© 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. 175948
    Prev
    Next
    INDEX
    Explanations

    names and specific job titles

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

    large-scale security software

    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
    墂
    0.50
    तन
    0.48
    昨天
    0.47
    ش
    0.47
    س
    0.47
    ان
    0.47
    肉
    0.47
    爷爷
    0.46
    ρεία
    0.46
    bott
    0.45
    POSITIVE LOGITS
    isen
    0.47
    өм
    0.47
    ón
    0.46
    isent
    0.45
    án
    0.44
     приня
    0.44
     thromb
    0.43
     मानते
    0.43
    oleh
    0.43
    imet
    0.43
    Activations Density 0.000%

    No Known Activations