© 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. 120856
    Prev
    Next
    INDEX
    Explanations

    purposes, scenarios, give you

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

    cybersecurity, web safety, and threats

    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
    namely
    0.52
    «
    0.49
    ท
    0.49
    時間
    0.48
    achim
    0.48
    "
    0.48
    ep
    0.47
    節
    0.46
     семья
    0.45
     вари
    0.44
    POSITIVE LOGITS
     preseason
    0.44
     Diocese
    0.43
     অজানা
    0.43
     সামান্য
    0.42
     onların
    0.42
     tại
    0.42
     assaults
    0.42
    燗
    0.42
    ảo
    0.41
     nameless
    0.41
    Activations Density 0.001%

    No Known Activations