© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103409
    Prev
    Next
    INDEX
    Explanations

    base path/component name

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

    the word "base" in code, particularly in variable names, file paths, and import statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h5>
    -1.74
     vivienda
    -1.54
    ","
    -1.48
    \
    -1.47
     it
    -1.46
    でしたが
    -1.44
     claridad
    -1.41
     soportes
    -1.41
     them
    -1.41
    ↵↵↵↵↵
    -1.41
    POSITIVE LOGITS
     チラシ
    1.49
    ꉂ
    1.45
    驀
    1.43
    讒
    1.41
     inconce
    1.41
     depl
    1.41
     perchance
    1.40
    Surprisingly
    1.39
    </strong>
    1.38
     特徴
    1.37
    Activations Density 0.004%

    No Known Activations