© 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. 101441
    Prev
    Next
    INDEX
    Explanations

    code delimiters and separators

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

    the bitwise OR operator (|) in code, particularly when combining flags or constants.

    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
    スポンサーリンク
    -1.63
    缡
    -1.61
    zewod
    -1.55
     penna
    -1.50
                  
    -1.50
    いま
    -1.49
     芋
    -1.48
    鶿
    -1.48
    隄
    -1.47
     –
    -1.45
    POSITIVE LOGITS
     einzigartigen
    1.63
     sicheren
    1.51
     echten
    1.51
     obcí
    1.48
     heiligen
    1.45
    ⅝
    1.44
     italienischen
    1.43
     französischen
    1.42
     případě
    1.40
     Şi
    1.40
    Activations Density 0.024%

    No Known Activations