© 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. 16453
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure commands

    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
    ного
    0.47
     пои
    0.45
    ꔰ
    0.45
    畱
    0.44
    ן
    0.43
     Bài
    0.43
    ⓪
    0.43
    皁
    0.43
    ם
    0.42
    ном
    0.42
    POSITIVE LOGITS
     technologies
    0.47
     dictum
    0.43
    的需求
    0.42
    的概念
    0.40
    _
    0.40
    IGN
    0.40
    rivation
    0.40
    4
    0.39
     implementations
    0.38
     SHOULD
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.