© 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. 248340
    Prev
    Next
    INDEX
    Explanations

    storage or electronic security

    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
    DSM
    0.55
    ACON
    0.50
    GSM
    0.47
    rogate
    0.47
    ACI
    0.47
    d
    0.47
    ETY
    0.46
    atletas
    0.46
    MODEL
    0.45
    诽
    0.45
    POSITIVE LOGITS
     won
    0.54
     gutted
    0.47
     Dutch
    0.46
     sẽ
    0.46
     kitt
    0.45
     domani
    0.45
     травня
    0.45
     Helmholtz
    0.45
    hens
    0.44
    ἢ
    0.44
    Activations Density 0.000%

    No Known Activations