© 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. 243297
    Prev
    Next
    INDEX
    Explanations

    business, years, minutes, attention

    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
     eso
    0.38
     đó
    0.37
     demikian
    0.37
     també
    0.37
    ;
    0.36
     также
    0.36
     także
    0.36
     soweit
    0.35
    လည်း
    0.34
    ‌شده
    0.33
    POSITIVE LOGITS
    .")]
    0.42
    Muito
    0.42
    ötzlich
    0.40
    Gravestone
    0.39
    >().
    0.38
     하나님의
    0.38
    কে
    0.37
     ہو۔
    0.37
    。」
    0.36
    名叫
    0.36
    Activations Density 0.003%

    No Known Activations