© 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. 11111
    Prev
    Next
    INDEX
    Explanations

    sterile, professional, infringing

    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
     게
    0.52
     Еў
    0.50
     हाथों
    0.49
     หมู่
    0.47
     薄
    0.47
     ForeignKey
    0.45
    िफ्ट
    0.45
     পেছন
    0.45
    𝕡
    0.45
     giv
    0.45
    POSITIVE LOGITS
    -
    0.60
    /
    0.53
    潭
    0.47
    EAR
    0.46
    Wor
    0.46
     verde
    0.46
    러스
    0.45
    Research
    0.45
     Melton
    0.44
    MULTI
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.