© 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. 37105
    Prev
    Next
    INDEX
    Explanations

    Apple addresses

    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_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
     مصنوع
    0.48
    =
    0.48
     the
    0.46
    ＝
    0.45
     utensils
    0.42
     detract
    0.42
    umably
    0.42
     पदार्थ
    0.40
    Ry
    0.40
    nbhd
    0.40
    POSITIVE LOGITS
    әр
    0.49
    ദു
    0.48
     ஜெய
    0.48
    埛
    0.47
     globales
    0.46
     desej
    0.46
    CTOGRAM
    0.45
     DISCLAIM
    0.44
    ૪
    0.44
     രാജ
    0.44
    Activations Density 0.002%

    No Known Activations