© 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. 45487
    Prev
    Next
    INDEX
    Explanations

    sweet fork

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

    lists, examples, or definitions

    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
     wacht
    0.55
    ள்ளை
    0.52
     negativos
    0.48
     nikdy
    0.48
     sustancias
    0.46
    ｂ
    0.45
     lined
    0.44
     ropa
    0.44
     liberación
    0.44
    ఎస్
    0.44
    POSITIVE LOGITS
    ch
    0.55
    sweet
    0.51
    fork
    0.49
    theory
    0.49
    cina
    0.49
    senior
    0.47
    ο
    0.47
    tid
    0.46
    causing
    0.46
    म
    0.46
    Activations Density 0.000%

    No Known Activations