© 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. 125006
    Prev
    Next
    INDEX
    Explanations

    contact you

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

    harm and vulnerability

    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
    ق
    0.50
     پوکر
    0.47
    と思いますが
    0.47
     এরকম
    0.45
     ক্রিকে
    0.45
     クロ
    0.44
     нрави
    0.44
    緬
    0.44
    cmml
    0.44
     डिफरेंट
    0.44
    POSITIVE LOGITS
    downloads
    0.49
    AX
    0.49
    achtung
    0.47
    Downloads
    0.46
    ate
    0.45
    gran
    0.45
    indicators
    0.43
    эд
    0.43
    ENSOR
    0.42
    ERK
    0.42
    Activations Density 0.000%

    No Known Activations