© 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. 78654
    Prev
    Next
    INDEX
    Explanations

    ensure safe operation

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

    lever, certificate, Quadrants, woman, binary, panel

    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
     determina
    0.45
    ๒
    0.44
    ۶
    0.43
    ۷
    0.42
    escue
    0.42
    真相
    0.42
    ւ
    0.42
    attacker
    0.41
    炽
    0.41
    UNITY
    0.41
    POSITIVE LOGITS
    ელს
    0.46
     gled
    0.45
    雱
    0.45
    ान्
    0.44
     postes
    0.44
     chauffeur
    0.44
     numérique
    0.42
    ูนย์
    0.42
     rara
    0.42
     récente
    0.42
    Activations Density 0.000%

    No Known Activations