© 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. 22-GEMMASCOPE-RES-131K
    7. 34196
    Prev
    Next
    INDEX
    Explanations

    `exports`

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

    This neuron detects code documentation markers and XML‐style doc tags (for example triple‐slash comments and `<…>`/`</…>` tags) in source files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     :
    -1.01
    ⠄
    -0.96
     física
    -0.95
     darbo
    -0.94
    CONCLUSIONES
    -0.93
    Törté
    -0.92
    Beskrivelse
    -0.90
    rees
    -0.89
    Kapcsolódó
    -0.89
    şek
    -0.88
    POSITIVE LOGITS
    がありますが
    0.94
    텀
    0.93
     Pardon
    0.90
    ̣n
    0.90
     $("<
    0.87
    並沒有
    0.86
    當初
    0.86
     eyeing
    0.85
     autentic
    0.84
    自从
    0.83
    Activations Density 0.009%

    No Known Activations