© 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. 45755
    Prev
    Next
    INDEX
    Explanations

    roles and skill checks

    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
    Tac
    0.47
     Gallows
    0.45
    甕
    0.44
    資本
    0.44
    噦
    0.44
    拋
    0.43
    gate
    0.43
    اتا
    0.43
    运用
    0.43
    Geb
    0.43
    POSITIVE LOGITS
     OHIO
    0.49
     ജോ
    0.47
     çıkan
    0.47
    {&
    0.46
     pés
    0.46
     fries
    0.46
    نت
    0.45
    िसोदिया
    0.45
     Fresno
    0.44
     huevos
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.