© 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. 8238
    Prev
    Next
    INDEX
    Explanations

    macros, conditional execution, values

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

    data types, values, strings

    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
    蟎
    0.40
    醗
    0.38
    दास
    0.38
    爺
    0.37
    餛
    0.36
    כּ
    0.36
    バレ
    0.36
     ಉಪಯೋಗ
    0.36
    憩
    0.36
    櫸
    0.36
    POSITIVE LOGITS
    Value
    0.52
     Value
    0.52
     Typed
    0.49
     Scalar
    0.48
     scalar
    0.47
     Node
    0.47
     trivial
    0.46
     typed
    0.45
     对象
    0.45
     value
    0.44
    Activations Density 0.077%

    No Known Activations