© 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. 11782
    Prev
    Next
    INDEX
    Explanations

    / html path separator

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

    URLs with paths

    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
     الشب
    0.37
    नी
    0.36
    AGC
    0.36
    IGH
    0.36
     ദുൽ
    0.35
    VI
    0.34
    ปล
    0.34
    居
    0.33
    ཚ
    0.33
    拥
    0.33
    POSITIVE LOGITS
    /,
    0.57
    /)
    0.52
    /?
    0.50
    /">
    0.50
    /),
    0.47
    /.
    0.46
    /",
    0.46
    /#
    0.44
    /',
    0.42
    foaf
    0.42
    Activations Density 0.025%

    No Known Activations