© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3700
    Prev
    Next
    INDEX
    Explanations

    surface qualities or tactility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    с
    2.09
    ون
    1.99
    ے
    1.88
    जनक
    1.74
    ح
    1.66
    िक
    1.63
    ين
    1.63
    ಿ
    1.58
    ва
    1.56
    ن
    1.56
    POSITIVE LOGITS
    ET
    1.81
     lifeless
    1.73
    að
    1.72
     pursuance
    1.68
    ार्किक
    1.68
     overhear
    1.65
    lgan
    1.63
    臾
    1.63
     resorting
    1.61
    橑
    1.61
    Activations Density 0.012%

    No Known Activations