© 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. 40270
    Prev
    Next
    INDEX
    Explanations

    booking appointments, flights, tours, clients

    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
    من
    1.91
    し
    1.84
    ousand
    1.80
    iv
    1.70
    なる
    1.68
    '
    1.66
    anging
    1.65
    .
    1.64
    에
    1.63
    ين
    1.63
    POSITIVE LOGITS
    渽
    2.17
    𝙎
    1.93
     Fungsi
    1.91
    𝙉
    1.91
    jogador
    1.88
    swers
    1.87
    ларга
    1.85
    etku
    1.85
    fono
    1.84
    ษัท
    1.83
    Activations Density 0.006%

    No Known Activations