© 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. 80855
    Prev
    Next
    INDEX
    Explanations

    gift baskets mobility sweeps building

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

    BOOKsy

    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
     bạch
    0.48
     прозра
    0.48
    朓
    0.44
     РО
    0.44
     広
    0.43
     Jeb
    0.43
     chy
    0.43
     thé
    0.42
     Voz
    0.42
     anybody
    0.42
    POSITIVE LOGITS
    fue
    0.48
    is
    0.47
    ій
    0.47
    يا
    0.46
    гура
    0.46
    1
    0.46
    BufferSize
    0.45
    ك
    0.45
    hein
    0.45
    ה
    0.45
    Activations Density 0.000%

    No Known Activations