© 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. 18989
    Prev
    Next
    INDEX
    Explanations

    html start tag

    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
     других
    0.43
     Outcomes
    0.42
    ệt
    0.42
    菣
    0.40
    駋
    0.39
    𝑍
    0.39
    <unused1011>
    0.39
     Utils
    0.39
    람
    0.39
     Export
    0.38
    POSITIVE LOGITS
    }$;
    0.43
     agua
    0.40
     cabeça
    0.40
    Glas
    0.39
     رئيس
    0.38
     agrad
    0.38
     edific
    0.38
     überras
    0.37
     litre
    0.37
     towering
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.