© 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. 220324
    Prev
    Next
    INDEX
    Explanations

    when assuming slip lash

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

    explaining concepts or examples

    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
     подчер
    0.45
    ungan
    0.44
     тепло
    0.43
    searchResults
    0.43
     fadeInLeft
    0.43
    🌡
    0.43
    ội
    0.42
    chaften
    0.42
    umba
    0.42
     وقف
    0.41
    POSITIVE LOGITS
    、
    0.47
     deleterious
    0.45
     use
    0.44
    御
    0.43
    的な
    0.43
    ">,</
    0.43
    シリーズ
    0.42
     suced
    0.42
    кци
    0.42
    CAT
    0.41
    Activations Density 0.000%

    No Known Activations