© 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. 213096
    Prev
    Next
    INDEX
    Explanations

    move forward

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

    describing aspects or characteristics

    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
    *
    0.57
    <0x0D>
    0.55
    >
    0.51
    mcs
    0.50
    metast
    0.50
    ئو
    0.49
    *,
    0.48
    ẹo
    0.48
    *.
    0.48
    ئا
    0.47
    POSITIVE LOGITS
     Yin
    0.47
     graça
    0.46
     multicultural
    0.46
     multicolor
    0.44
     siv
    0.44
    にかく
    0.44
     éxitos
    0.44
     প্রয
    0.44
     прогре
    0.44
     thème
    0.44
    Activations Density 0.000%

    No Known Activations