© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 397
    Prev
    Next
    INDEX
    Explanations

    rental locations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects natural, conversational language and engaging narrative text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @jamesnaruto04

    Tokens or short sequences that appear to be the beginning of a request, question, or instruction, often functioning as introductory phrases that set up what the user wants to know or have done.

    eleuther_acts_top20 · claude-4-5-sonnetTriggered by @jamesnaruto04
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siden
    0.22
     rele
    0.20
     timeframe
    0.20
     defini
    0.20
     jų
    0.20
     scru
    0.20
    ucidation
    0.20
     especial
    0.20
     terminology
    0.20
     ferram
    0.20
    POSITIVE LOGITS
     женщины
    0.24
    宠物
    0.24
     반려동
    0.24
    restaurant
    0.23
     کودکان
    0.23
     животных
    0.22
     Restaurant
    0.22
    婴儿
    0.22
    农村
    0.22
    Airbnb
    0.22
    Activations Density 8.966%

    No Known Activations