© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34740
    Prev
    Next
    INDEX
    Explanations

    book store, tree, intro, Miller

    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
    Negative Logits
     веду
    0.84
     denominado
    0.83
     интеллек
    0.82
    ті
    0.81
    S
    0.80
    та
    0.78
    h
    0.75
    saver
    0.75
    hain
    0.74
    Hispanic
    0.74
    POSITIVE LOGITS
     総
    0.88
    اً
    0.88
     Smile
    0.74
    ються
    0.71
    ється
    0.70
    ර්ශ
    0.70
     Vak
    0.69
    োপুরি
    0.69
     dépens
    0.68
     Renewal
    0.68
    Activations Density 0.000%

    No Known Activations