© 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. 240479
    Prev
    Next
    INDEX
    Explanations

    Group rates

    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
    OC
    0.57
    OPLE
    0.46
    opy
    0.44
    IVOS
    0.43
    пример
    0.43
     செயலா
    0.43
    ുവെ
    0.42
    唂
    0.42
    똑
    0.41
    OD
    0.40
    POSITIVE LOGITS
    t
    0.46
    嫡
    0.42
     preferable
    0.41
     preferencia
    0.41
    prefer
    0.40
     Lag
    0.39
     covari
    0.39
    rova
    0.39
     comma
    0.38
     Mocha
    0.38
    Activations Density 0.001%

    No Known Activations