© 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. 209050
    Prev
    Next
    INDEX
    Explanations

    actions and entities

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

    cause and effect

    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
     therapist
    0.47
     contado
    0.47
     legis
    0.47
     robot
    0.44
     empleado
    0.44
     OUTPUT
    0.44
     planilla
    0.43
     以
    0.42
     asesor
    0.42
     predom
    0.42
    POSITIVE LOGITS
    RouteChange
    0.46
    叽
    0.45
     الجديدة
    0.43
    Queue
    0.42
    Copper
    0.42
    Clamp
    0.42
    cov
    0.42
    است
    0.41
     revê
    0.41
    ەی
    0.41
    Activations Density 0.001%

    No Known Activations