© 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. 40-GEMMASCOPE-2-RES-262K
    7. 16266
    Prev
    Next
    INDEX
    Explanations

    modal verbs and negation with actions

    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_40_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
     తమ
    0.47
     pouvant
    0.46
     নিজেরাই
    0.44
    尋
    0.41
     themselves
    0.41
     தங்கள்
    0.40
    TableModel
    0.39
    ラグ
    0.39
     сами
    0.39
     過
    0.38
    POSITIVE LOGITS
     beho
    0.84
     snowing
    0.73
     habido
    0.71
     raining
    0.64
     rained
    0.63
     wasn
    0.61
    inerary
    0.58
     happened
    0.58
     happen
    0.55
     doesn
    0.54
    Activations Density 0.016%

    No Known Activations