© 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. 185931
    Prev
    Next
    INDEX
    Explanations

    mbrola, Psaki

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

    universal ethical concerns

    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
    ättning
    0.39
     ji
    0.39
    ibilité
    0.39
     τά
    0.38
    垟
    0.38
     kendaraan
    0.37
     satta
    0.36
     tai
    0.36
    ském
    0.36
    и
    0.36
    POSITIVE LOGITS
    slam
    0.43
    POS
    0.40
    GPIO
    0.40
     Smol
    0.39
    digest
    0.39
    sendLog
    0.39
    消化
    0.39
     obligado
    0.39
    AME
    0.39
    Digest
    0.38
    Activations Density 0.000%

    No Known Activations