© 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. 193867
    Prev
    Next
    INDEX
    Explanations

    percentage of

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

    happens, handles, speeding, lives

    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
    LOTRE
    0.52
    ką
    0.50
    nl
    0.49
     punctato
    0.49
     köş
    0.49
    yloxy
    0.47
    かります
    0.47
    䆔
    0.46
    ओं
    0.46
     sujeto
    0.46
    POSITIVE LOGITS
    <0x0D>
    0.62
    ↵↵↵↵↵↵
    0.56
    ↵↵↵↵↵
    0.53
    ↵↵↵↵
    0.50
    venture
    0.49
    und
    0.49
    ↵↵↵↵↵↵↵↵
    0.48
    ...
    0.48
    <h3>
    0.46
    <h2>
    0.46
    Activations Density 0.000%

    No Known Activations