© 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. 67372
    Prev
    Next
    INDEX
    Explanations

    Kamala Khan, tech program, computer vulnerabilities

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

    honest frankness or directness

    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
     Watts
    0.66
     in
    0.57
     or
    0.57
     Vaughn
    0.57
     ENS
    0.55
     Vaughan
    0.54
    m
    0.52
    in
    0.52
     Burns
    0.50
     Memoirs
    0.50
    POSITIVE LOGITS
    Cancel
    0.54
    Customize
    0.48
     customizable
    0.47
     څنګه
    0.47
     scrumptious
    0.46
     அதிசய
    0.45
     پیشن
    0.45
     میلیون
    0.43
     pooch
    0.43
     红
    0.43
    Activations Density 0.001%

    No Known Activations