© 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. 110685
    Prev
    Next
    INDEX
    Explanations

    large numbers referring to quantity

    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
    長く
    0.44
     বড়
    0.42
    few
    0.42
     few
    0.40
    術
    0.40
    Important
    0.39
    Consec
    0.38
    术
    0.37
     namely
    0.37
    几个
    0.37
    POSITIVE LOGITS
     thousand
    1.11
    thousand
    0.85
     тысяч
    0.80
     hundred
    0.79
     million
    0.79
     Thousand
    0.75
     ஆயிரம்
    0.75
     тыся
    0.74
     тысячи
    0.68
     thousands
    0.68
    Activations Density 0.016%

    No Known Activations