© 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. 55359
    Prev
    Next
    INDEX
    Explanations

    read: only complete

    np_acts-logits-general · gemini-2.5-flash-lite

    avoid processing politics lost visa write align

    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
    צ
    0.45
    必备
    0.43
     Eigenschaften
    0.42
    }.",
    0.41
    γά
    0.40
    鿌
    0.40
     exponents
    0.40
    oshin
    0.40
    👰
    0.40
     confines
    0.40
    POSITIVE LOGITS
     प्रत्य
    0.44
     metabolism
    0.42
     聞い
    0.42
    судар
    0.42
     Cur
    0.41
     Тру
    0.41
     Melville
    0.41
     perror
    0.40
    НГ
    0.40
     naal
    0.40
    Activations Density 0.000%

    No Known Activations