© 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. 206563
    Prev
    Next
    INDEX
    Explanations

    official or administrative information

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

    explaining concepts and how

    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
     Mitochond
    0.48
     Photograph
    0.46
    Ω
    0.45
    一般的な
    0.45
    JC
    0.43
    ரிக்க
    0.42
     पोहो
    0.42
     Gespräch
    0.42
    嶙
    0.42
     Timer
    0.41
    POSITIVE LOGITS
     admissibility
    0.48
     subsequently
    0.46
    ueless
    0.44
    стта
    0.44
    Allowed
    0.43
     Sterling
    0.43
    rát
    0.43
     irreducible
    0.42
    ίν
    0.42
    aat
    0.42
    Activations Density 0.000%

    No Known Activations