© 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. 26678
    Prev
    Next
    INDEX
    Explanations

    command-line options and flags

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

    command-line flags

    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
    দার
    0.35
    WELL
    0.35
    हा
    0.33
    য়ং
    0.33
    বাড়
    0.33
    north
    0.33
    ения
    0.33
    $("#
    0.32
    फाली
    0.32
    为何
    0.32
    POSITIVE LOGITS
     ako
    0.34
     ಮಾತ್ರ
    0.33
     virtud
    0.32
     숫
    0.31
     pulsating
    0.30
     negativ
    0.30
     întreb
    0.30
     ese
    0.30
     நிமிடங்கள்
    0.30
     ^
    0.30
    Activations Density 0.000%

    No Known Activations