© 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. 80448
    Prev
    Next
    INDEX
    Explanations

    saved or saving lives

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

    vulnerable to existential threats or risks

    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
    ედა
    0.51
    funciones
    0.50
     চেহারা
    0.48
    ógł
    0.48
    ვ
    0.48
    ေ
    0.48
    füll
    0.47
    Josef
    0.47
    LookAnd
    0.46
    ZIP
    0.46
    POSITIVE LOGITS
     lower
    0.52
     Livestock
    0.47
    挛
    0.46
     livestock
    0.45
    socketState
    0.45
     Sb
    0.45
     crossing
    0.45
     Lower
    0.45
     catfish
    0.45
     cough
    0.45
    Activations Density 0.000%

    No Known Activations