© 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. 103189
    Prev
    Next
    INDEX
    Explanations

    URLs and identifiers

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

    base64-encoded or other encoded binary data strings.

    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
    ’
    -2.78
     If
    -2.38
     assorted
    -2.31
     zufried
    -2.27
     höchst
    -2.25
     vorkommen
    -2.22
     schwerer
    -2.20
     whol
    -2.20
    .
    -2.19
    素晴らしい
    -2.14
    POSITIVE LOGITS
    er
    2.80
    ſſer
    2.48
    e
    2.34
    点は
    2.33
    0
    2.31
    瞑
    2.28
     romana
    2.27
    SE
    2.23
    蜩
    2.17
     ſch
    2.16
    Activations Density 0.019%

    No Known Activations