© 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. 80208
    Prev
    Next
    INDEX
    Explanations

    locations and actions

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

    definition or description

    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
    汅
    0.46
    ERGY
    0.46
    >)</
    0.45
    ዜ
    0.45
    ISES
    0.44
    >≤</
    0.44
     mij
    0.44
     immor
    0.44
     QR
    0.43
     रजिस्ट्री
    0.43
    POSITIVE LOGITS
    踽
    0.46
     JOptionPane
    0.46
    Myth
    0.44
    その他
    0.43
    𝗮
    0.42
    、【
    0.42
     তখনকার
    0.42
    ה
    0.42
     voorzien
    0.41
    、
    0.41
    Activations Density 0.000%

    No Known Activations