© 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. 187511
    Prev
    Next
    INDEX
    Explanations

    internet terms to share

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

    general considerations

    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
    ann
    0.47
     Except
    0.45
    D
    0.44
    ugg
    0.43
     except
    0.41
    er
    0.41
    Â
    0.41
     Dec
    0.40
    :
    0.40
    il
    0.40
    POSITIVE LOGITS
     nuestras
    0.63
     barrios
    0.57
     branco
    0.55
     legislatures
    0.55
     системы
    0.54
     puertos
    0.54
     nossas
    0.53
     nuestros
    0.53
     voltmeter
    0.52
     वैशिष्ट
    0.52
    Activations Density 0.007%

    No Known Activations