© 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. 122331
    Prev
    Next
    INDEX
    Explanations

    conditionals, possibilities, entities, and thresholds

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

    mind processes and structures

    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
    嗕
    0.46
    เซ
    0.46
    แ
    0.45
    เป
    0.45
    रित
    0.44
    金を
    0.44
    廰
    0.44
    分
    0.43
    ネタ
    0.43
    さまざまな
    0.42
    POSITIVE LOGITS
     patrimonio
    0.54
     domicilio
    0.48
     famiglia
    0.48
     bordo
    0.46
     remod
    0.46
     categorie
    0.46
     modificación
    0.46
     cambio
    0.45
     categoria
    0.45
     grom
    0.45
    Activations Density 0.001%

    No Known Activations