© 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. 5956
    Prev
    Next
    INDEX
    Explanations

    key-value pairs with separators

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

    key-value assignment

    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
    หลด
    0.33
    瓈
    0.33
    GEBURTS
    0.31
     автоматтарын
    0.31
     ሌሎች
    0.31
     नावा
    0.31
    下來
    0.30
     थांब
    0.30
     ሰዎች
    0.30
    ጨም
    0.30
    POSITIVE LOGITS
    ="
    0.57
     and
    0.56
    =
    0.50
     và
    0.48
     =
    0.47
     и
    0.42
     και
    0.41
     و
    0.40
    and
    0.39
     $=
    0.39
    Activations Density 0.030%

    No Known Activations