© 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. 16130
    Prev
    Next
    INDEX
    Explanations

    security alert

    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
    الإ
    0.57
    is
    0.49
    ma
    0.48
    ជាមួយនឹង
    0.47
    o
    0.47
    le
    0.45
    í
    0.45
    絕對
    0.45
    я
    0.45
    uga
    0.44
    POSITIVE LOGITS
     yanlı
    0.49
     شمار
    0.49
     tau
    0.48
     fanden
    0.47
     rusak
    0.46
     cukup
    0.45
     matematika
    0.45
     karbon
    0.45
     perang
    0.44
     musik
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.