© 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. 154292
    Prev
    Next
    INDEX
    Explanations

    motor carriers, blogs, business, welders, laughter

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

    illegal activity and agriculture

    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
    စာ
    0.47
    ،
    0.47
    ATUM
    0.46
    🎟
    0.46
    ，
    0.45
    είται
    0.44
    ی
    0.44
    🎫
    0.43
     می‌شود
    0.43
    🚃
    0.43
    POSITIVE LOGITS
     agricult
    0.49
     abusive
    0.47
     ilegal
    0.47
     illegal
    0.45
     therapeut
    0.45
     illeg
    0.45
     हमेशा
    0.45
    ɠ
    0.44
     abus
    0.44
     abogados
    0.44
    Activations Density 0.000%

    No Known Activations