© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64056
    Prev
    Next
    INDEX
    Explanations

    first language

    np_acts-logits-general · gemini-2.5-flash-lite

    development and origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adeh
    0.46
    Particip
    0.44
    心地
    0.44
    مق
    0.44
    ಡೆಯ
    0.43
    당
    0.43
    жа
    0.43
    𝘇
    0.42
    囷
    0.42
    serve
    0.41
    POSITIVE LOGITS
     pb
    0.49
     sviluppo
    0.47
     чём
    0.46
     toolkit
    0.46
     teoría
    0.46
     movimiento
    0.45
     cosidd
    0.45
     cd
    0.44
     mécanisme
    0.44
     seç
    0.44
    Activations Density 0.000%

    No Known Activations