© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17470
    Prev
    Next
    INDEX
    Explanations

    cap and lid closures

    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_16_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
     are
    0.71
    ;
    0.70
     array
    0.68
     telo
    0.67
     ident
    0.66
     art
    0.64
     elev
    0.63
     identifiers
    0.63
     elements
    0.63
     items
    0.62
    POSITIVE LOGITS
    蓋
    0.81
    bottlecap
    0.80
    캡
    0.68
    キャップ
    0.68
    盖
    0.65
    lid
    0.64
    after
    0.64
    cap
    0.63
    𝓃
    0.62
    ьо
    0.61
    Activations Density 0.007%

    No Known Activations