© 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. 227827
    Prev
    Next
    INDEX
    Explanations

    settings, configurations, or specific types

    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
    計画
    0.45
    gó
    0.44
    vindos
    0.43
    ggg
    0.43
    p
    0.42
    河
    0.42
     apoy
    0.42
     revolving
    0.42
    durch
    0.41
    Together
    0.41
    POSITIVE LOGITS
    ক্তি
    0.43
     deviceInfo
    0.43
     Comput
    0.43
    疮
    0.42
    க்கே
    0.41
     চুলের
    0.41
     centimetres
    0.41
     incremento
    0.41
     малень
    0.41
     fontSize
    0.40
    Activations Density 0.000%

    No Known Activations