© 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. 102350
    Prev
    Next
    INDEX
    Explanations

    api documentation and calls

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

    references to API calls, methods, or endpoints in programming contexts.

    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
     ‘
    -2.39
     —
    -2.25
    ‘
    -2.13
    ’,
    -2.03
    9
    -2.00
    2
    -1.98
     opulent
    -1.91
    ’
    -1.89
    1
    -1.85
    尤其
    -1.83
    POSITIVE LOGITS
    銩
    2.14
    )،
    2.09
    廛
    2.08
    geſ
    2.03
    滙
    1.98
    嗞
    1.82
     cilindros
    1.81
    Ᏺ
    1.77
    kemeja
    1.76
     mitochond
    1.73
    Activations Density 0.018%

    No Known Activations