© 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. 42833
    Prev
    Next
    INDEX
    Explanations

    operators, expansion, and

    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
    வின்
    0.48
    tareas
    0.42
    サービスの
    0.42
    inicio
    0.42
     преимущественно
    0.42
    鹧
    0.42
    லத்தில்
    0.41
    glColor
    0.41
    สัม
    0.40
     rechte
    0.40
    POSITIVE LOGITS
     و
    0.49
     и
    0.46
     داعش
    0.45
     ול
    0.44
     and
    0.44
     &
    0.43
    ？」
    0.42
    ＆
    0.41
     allowable
    0.40
     και
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.