© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113679
    Prev
    Next
    INDEX
    Explanations

    method and attribute declarations

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

    whitespace indentation at the beginning of lines, particularly in code blocks.

    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
    Gön
    -1.92
    Tür
    -1.57
    Jangan
    -1.55
    Bukan
    -1.54
     retira
    -1.52
    Mä
    -1.52
    emballage
    -1.51
    ž
    -1.50
    Läh
    -1.49
    Öl
    -1.47
    POSITIVE LOGITS
    龊
    1.65
     such
    1.62
     exceedingly
    1.52
    is
    1.48
     is
    1.45
    self
    1.44
     sonhos
    1.43
     
    1.41
    genta
    1.40
     dreadful
    1.38
    Activations Density 0.008%

    No Known Activations