© 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. 65052
    Prev
    Next
    INDEX
    Explanations

    Regional anesthesia

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

    line break or paragraph markers in technical or academic documents.

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

    The neuron activates on decimal‐point numeric values (floating‐point numbers) in the text.

    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
    łko
    -1.09
     vode
    -1.07
     kerusakan
    -1.05
    лни
    -1.02
    también
    -1.02
    ERATION
    -1.02
    ाला
    -1.00
    ~~~~~
    -1.00
    ofing
    -0.98
    omsday
    -0.98
    POSITIVE LOGITS
     revamped
    1.03
     amount
    1.01
    should
    0.94
    點
    0.93
     каких
    0.92
     ιδ
    0.91
     unearth
    0.91
    John
    0.91
     Главная
    0.89
    Joe
    0.88
    Activations Density 0.000%

    No Known Activations