© 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. 96485
    Prev
    Next
    INDEX
    Explanations

    Slack workspace

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

    handling cases and actions

    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
     movimientos
    0.48
     introducir
    0.48
     colocar
    0.46
     בין
    0.46
     movimentos
    0.46
     उद्योग
    0.46
     wechsel
    0.45
    鉑
    0.44
     mouvements
    0.44
     coloque
    0.44
    POSITIVE LOGITS
    AGEN
    0.44
    st
    0.44
     ويب
    0.43
    POL
    0.42
    grounds
    0.42
    PIO
    0.40
    fully
    0.40
    濃
    0.40
    COO
    0.39
     contracting
    0.39
    Activations Density 0.000%

    No Known Activations