© 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. 67482
    Prev
    Next
    INDEX
    Explanations

    my, your

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

    Bitcoin, shared, eternal

    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
    ’
    0.61
    NOT
    0.52
     pheasant
    0.50
     terrorism
    0.50
     caliper
    0.50
     tubing
    0.48
     battery
    0.48
     calibration
    0.48
    dx
    0.48
    authorization
    0.48
    POSITIVE LOGITS
     វា
    0.61
     써
    0.55
    <0x0D>
    0.54
     ద
    0.49
     упо
    0.47
     Бога
    0.47
     బంగ
    0.46
    忶
    0.46
    StructOf
    0.46
    িতে
    0.46
    Activations Density 0.001%

    No Known Activations