© 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. 186442
    Prev
    Next
    INDEX
    Explanations

    email on, Beautiful skies

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

    rationalize faith prioritizing security

    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
    हल
    0.59
     работ
    0.52
    rych
    0.46
     הראשון
    0.45
     தெரிவித்தனர்
    0.45
     начал
    0.43
    thema
    0.43
    率
    0.43
    cannot
    0.42
    োপা
    0.42
    POSITIVE LOGITS
     CGI
    0.53
     LiDAR
    0.43
     dispositivi
    0.43
     niin
    0.43
     sil
    0.41
     generic
    0.41
     corde
    0.41
     SOD
    0.41
     headroom
    0.41
     Honolulu
    0.41
    Activations Density 0.000%

    No Known Activations