© 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. 100840
    Prev
    Next
    INDEX
    Explanations

    significance, income, installation, safety, areas

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

    blocking malicious IPs

    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
    Ii
    0.45
    িনার
    0.45
     Twelfth
    0.44
     Balloons
    0.44
    鰍
    0.44
    selector
    0.43
     Stabil
    0.43
     FGD
    0.43
    িয়ান
    0.43
     Committees
    0.43
    POSITIVE LOGITS
    м
    0.49
    راحة
    0.46
     violation
    0.46
     razy
    0.46
     chauffage
    0.45
    elijk
    0.44
    лл
    0.44
    лды
    0.43
    ForRule
    0.42
     adultery
    0.42
    Activations Density 0.000%

    No Known Activations