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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249717
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    ellten
    0.48
     অনি
    0.47
    binomial
    0.46
    페이지
    0.46
    𝜁
    0.45
    REGISTER
    0.43
    elementAt
    0.43
    ClNO
    0.42
    PREFIX
    0.41
    Assignable
    0.41
    POSITIVE LOGITS
     hull
    0.51
     juga
    0.50
     gì
    0.47
     discount
    0.47
     vlog
    0.46
     also
    0.46
     video
    0.45
    و
    0.45
     premiere
    0.45
     sort
    0.45
    Activations Density 0.010%

    No Known Activations