© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8615
    Prev
    Next
    INDEX
    Explanations

    code configuration and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    |
    0.86
     the
    0.78
     The
    0.74
    捒
    0.69
    The
    0.68
    <unused2199>
    0.66
     reigning
    0.66
     وهذا
    0.66
     respectable
    0.65
     arguably
    0.64
    POSITIVE LOGITS
     AutoML
    0.92
    ⸨
    0.84
    WebSocket
    0.82
    GetAll
    0.82
    গীত
    0.82
    getConfig
    0.82
    toJson
    0.81
    Ꮺ
    0.80
     WebSocket
    0.80
    ptitle
    0.80
    Activations Density 0.124%

    No Known Activations