© 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. 238235
    Prev
    Next
    INDEX
    Explanations

    locations and entities

    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
     إذا
    0.52
     دي
    0.50
     topRight
    0.50
    ت
    0.48
     Gord
    0.47
    。《
    0.47
    ല്ലാതെ
    0.46
     sert
    0.46
     البل
    0.46
    ဿ
    0.46
    POSITIVE LOGITS
     LOCATION
    0.48
    ↵
    0.48
    刚刚
    0.44
    is
    0.43
    ere
    0.43
    헉
    0.42
    oretum
    0.42
    IS
    0.40
    kih
    0.40
    igheid
    0.40
    Activations Density 0.001%

    No Known Activations