© 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. 99478
    Prev
    Next
    INDEX
    Explanations

    or and not

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

    akin to handing out bank account passwords

    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
     Aś
    0.56
     이걸
    0.50
     kommun
    0.48
     싫
    0.47
     imprison
    0.47
     něk
    0.46
     otáz
    0.46
     insbesondere
    0.46
     イヤ
    0.45
    ᓗ
    0.45
    POSITIVE LOGITS
    1
    0.57
    receive
    0.55
    standard
    0.52
    P
    0.48
     receive
    0.47
    ALL
    0.47
    Received
    0.46
    received
    0.46
    F
    0.45
    dal
    0.44
    Activations Density 0.001%

    No Known Activations