© 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. 26238
    Prev
    Next
    INDEX
    Explanations

    offering help with tasks

    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
     realización
    0.55
     medicamento
    0.51
     escucha
    0.51
    ައް
    0.50
     honda
    0.50
    冑
    0.49
     factura
    0.49
     cantidad
    0.48
     equação
    0.48
     legít
    0.48
    POSITIVE LOGITS
    i
    0.63
    el
    0.60
    ör
    0.52
    aj
    0.51
    del
    0.51
    et
    0.50
     接
    0.49
    eth
    0.49
    ui
    0.48
    per
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.