© 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. 179405
    Prev
    Next
    INDEX
    Explanations

    steel file, ix bar, also enables

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

    identifying points or categories

    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
    edk
    0.49
     cookbooks
    0.48
    nouns
    0.48
    truths
    0.48
    nextLine
    0.47
    ")),
    0.47
    +}(
    0.46
    moires
    0.46
    etchup
    0.46
    cucumber
    0.46
    POSITIVE LOGITS
    告示
    0.45
     Laguna
    0.45
     confer
    0.43
    阿
    0.43
    瘴
    0.43
    ನ್
    0.43
    LAG
    0.42
     crow
    0.42
     dabei
    0.42
    予
    0.42
    Activations Density 0.000%

    No Known Activations