© 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. 18167
    Prev
    Next
    INDEX
    Explanations

    software packages and libraries

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

    python code blocks

    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
     Fleurit
    0.32
    strMeal
    0.31
     pohy
    0.31
     %``
    0.30
     poitrine
    0.30
    rawberry
    0.30
     vyroben
    0.29
     êtres
    0.29
    emetery
    0.28
    ⛧
    0.28
    POSITIVE LOGITS
    Environment
    0.32
    Utils
    0.31
    AccessException
    0.31
    utils
    0.30
     integration
    0.30
     infrastructure
    0.29
    可能
    0.29
     native
    0.29
     Environment
    0.29
     Utils
    0.29
    Activations Density 0.000%

    No Known Activations