© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66467
    Prev
    Next
    INDEX
    Explanations

    hypertensive rats

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

    programming and technical elements like code syntax, package names, and documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on main content nouns (often technical or domain‐specific terms) in code or prose.

    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
    superdry
    -1.00
     vacacionales
    -0.98
    Zdroj
    -0.98
    ventilador
    -0.96
    はこちらから
    -0.95
    piscina
    -0.91
    hdysval
    -0.91
     manqué
    -0.90
     eenige
    -0.89
     professeurs
    -0.89
    POSITIVE LOGITS
     Nang
    0.98
     potest
    0.92
    徳島
    0.92
     Puy
    0.89
    发生了
    0.89
     ¨
    0.89
     rodriguez
    0.87
    āb
    0.84
    o
    0.83
    go
    0.81
    Activations Density 0.017%

    No Known Activations