© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9787
    Prev
    Next
    INDEX
    Explanations

    offers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    D
    0.46
    metadata
    0.45
    Department
    0.43
    Context
    0.41
    H
    0.41
    em
    0.40
    F
    0.40
    header
    0.39
    enc
    0.39
    facility
    0.39
    POSITIVE LOGITS
     unethical
    0.53
     Vegan
    0.45
     cheeky
    0.44
     vegan
    0.44
     Giveaway
    0.44
    碖
    0.42
     आश्चर्य
    0.41
     экологи
    0.40
     booty
    0.40
     реально
    0.40
    Activations Density 0.479%

    No Known Activations