© 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. 4882
    Prev
    Next
    INDEX
    Explanations

    online platforms

    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
    C
    0.90
    L
    0.87
    r
    0.86
    fro
    0.78
    faz
    0.77
    ㅡ
    0.77
     incessantly
    0.75
    f
    0.75
    जिद
    0.75
    mDatas
    0.75
    POSITIVE LOGITS
     nét
    0.88
     deserialize
    0.88
     vignettes
    0.88
    他們
    0.87
     suffisante
    0.87
    '%(
    0.83
    هم
    0.82
    '%
    0.82
     {|
    0.82
    ﻱ
    0.82
    Activations Density 0.208%

    No Known Activations