© 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. 190148
    Prev
    Next
    INDEX
    Explanations

    leader and

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

    storage speed, emotions, development

    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
    ।
    0.55
    स
    0.52
     निर्मित
    0.50
     menyel
    0.48
    人々
    0.48
    ंना
    0.48
     menarik
    0.48
     be
    0.47
    \|,
    0.47
    oscow
    0.47
    POSITIVE LOGITS
     وك
    0.52
     CRUZ
    0.46
     flamingo
    0.44
     apud
    0.44
     عندي
    0.43
     Escola
    0.42
    wagon
    0.42
     Flamingo
    0.42
     Carn
    0.42
     absol
    0.41
    Activations Density 0.000%

    No Known Activations