© 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. 100892
    Prev
    Next
    INDEX
    Explanations

    reference. beds. makers

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

    game intel or motivation

    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
     obscurity
    0.50
    GOB
    0.48
    WhiteBalance
    0.47
     claridad
    0.47
    괵
    0.47
    ApiPath
    0.46
     intimidating
    0.46
    டு
    0.46
     introspection
    0.46
     illustrious
    0.45
    POSITIVE LOGITS
    ings
    0.49
    ter
    0.48
     berkaitan
    0.46
    beds
    0.46
    der
    0.45
    o
    0.45
    bed
    0.45
    ref
    0.45
     খু
    0.45
    makers
    0.45
    Activations Density 0.002%

    No Known Activations