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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60269
    Prev
    Next
    INDEX
    Explanations

    names, code, specifics

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

    The neuron fires on common English function words (very high‐frequency “stop words” like he, the, is, to, and, at, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻟ
    -0.77
     ATTACK
    -0.73
    Clothing
    -0.72
     सही
    -0.71
     Sprung
    -0.70
    ﻱ
    -0.70
     attaque
    -0.69
    riages
    -0.69
     tuyo
    -0.68
     ම
    -0.68
    POSITIVE LOGITS
    半年
    0.66
    Tron
    0.65
     има
    0.65
    róleo
    0.65
     Oyster
    0.65
    asha
    0.65
    fulfilled
    0.64
     reflected
    0.64
    rics
    0.63
     Schie
    0.63
    Activations Density 0.051%

    No Known Activations