© 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. 37994
    Prev
    Next
    INDEX
    Explanations

    local business

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

    gain from sunlight warming

    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
    WinCounter
    0.53
     ئۇ
    0.52
     обозна
    0.52
    Noeud
    0.51
    冋
    0.50
     وزیر
    0.49
    Fog
    0.49
     ئى
    0.49
    FixedHeight
    0.49
     обли
    0.48
    POSITIVE LOGITS
     average
    0.49
    ovanje
    0.46
    itaj
    0.46
     motorcycles
    0.44
    ല
    0.43
    攜
    0.43
    ل
    0.43
    が多い
    0.42
    encie
    0.42
    ರ್ಷ
    0.42
    Activations Density 0.000%

    No Known Activations