© 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. 394
    Prev
    Next
    INDEX
    Explanations

    `[Tooltip]` descriptions

    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
    ఖా
    0.38
    +%
    0.37
    转型
    0.34
    știg
    0.33
    ┄
    0.33
    стви
    0.32
    帧
    0.32
     эф
    0.31
    ះ
    0.31
    -"+
    0.31
    POSITIVE LOGITS
    This
    0.46
     This
    0.45
    The
    0.41
    Hint
    0.40
     Debye
    0.40
     Note
    0.39
     The
    0.39
     Emphasis
    0.39
     Cause
    0.38
     excludes
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.