© 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. 16810
    Prev
    Next
    INDEX
    Explanations

    needs . war on Make sure disturbing , other goods of the a fact many collections

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

    direct heat

    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
     Ка
    0.35
     图
    0.34
     $(-
    0.34
     acabado
    0.34
     Szen
    0.34
    -(-
    0.32
    𝘫
    0.32
     sano
    0.31
     argv
    0.31
    }}=-
    0.31
    POSITIVE LOGITS
    UNCIL
    0.44
    ouncil
    0.38
    Disclosure
    0.38
    proj
    0.38
    semibold
    0.38
    aclysm
    0.37
    bladder
    0.37
    ylinder
    0.36
    evole
    0.35
     intruders
    0.35
    Activations Density 0.000%

    No Known Activations