© 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. 28273
    Prev
    Next
    INDEX
    Explanations

    programming contexts or data types

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

    constructor new

    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
    avacanam
    0.55
     самых
    0.50
    蒺
    0.47
    スの
    0.47
    avkhat
    0.47
     Франции
    0.44
    FBSDKAppEvents
    0.43
    ंच्या
    0.43
    ®.
    0.42
    ₪
    0.42
    POSITIVE LOGITS
    ，
    0.55
     I
    0.52
    ،
    0.52
     =
    0.51
    或
    0.49
     أو
    0.46
     lawns
    0.45
     drill
    0.44
     বা
    0.43
    或者
    0.43
    Activations Density 0.000%

    No Known Activations