© 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. 212781
    Prev
    Next
    INDEX
    Explanations

    availability of, must be

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

    Vocabulary, sugar, choice, function, logic, descriptive terms

    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
    label
    0.50
     captain
    0.49
     handsome
    0.48
    this
    0.46
     German
    0.45
    currentPlayer
    0.45
     Marathon
    0.44
    w
    0.44
     Black
    0.44
    jPanel
    0.43
    POSITIVE LOGITS
    蕩
    0.50
     своє
    0.48
    跡
    0.48
    騁
    0.47
    𒀝
    0.47
     ಬೆ
    0.47
    經濟
    0.46
     atteints
    0.46
     дітей
    0.46
    ін
    0.46
    Activations Density 0.000%

    No Known Activations