© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5285
    Prev
    Next
    INDEX
    Explanations

    references like [Number]

    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_16k_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
    ्स
    0.93
    ции
    0.84
    ेट
    0.80
    ių
    0.78
    서
    0.77
    ب
    0.76
    த்தில்
    0.73
     والإ
    0.72
    కు
    0.71
    Ћ
    0.69
    POSITIVE LOGITS
    nYou
    0.90
    ра
    0.81
    ння
    0.79
     사항
    0.77
    varande
    0.77
    豊かな
    0.77
    𝙔
    0.77
    他
    0.77
     you
    0.76
    emptive
    0.75
    Activations Density 0.007%

    No Known Activations