© 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. 49640
    Prev
    Next
    INDEX
    Explanations

    own favourite

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

    distribution, analysis, yourself, tool

    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
    <0xA7>
    0.50
    Payroll
    0.50
    ]));
    0.48
    ():
    0.48
    :
    0.46
    "
    0.44
    Scott
    0.44
    Guidelines
    0.44
    +
    0.43
    更多
    0.43
    POSITIVE LOGITS
     Κο
    0.48
     hexagon
    0.47
     olig
    0.47
     espèce
    0.47
     Λ
    0.47
     spleen
    0.47
     Ξ
    0.47
     Stomach
    0.47
     Verstappen
    0.46
     guiclass
    0.46
    Activations Density 0.000%

    No Known Activations