© 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. 43077
    Prev
    Next
    INDEX
    Explanations

    dc voltage input

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

    The neuron activates on numeric voltage specifications (e.g. values followed by “V,” “VDC,” or “DC”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     gave
    -2.20
     made
    -2.08
     That
    -2.06
     used
    -2.03
     went
    -1.91
     What
    -1.86
    って思
    -1.85
     Even
    -1.84
     with
    -1.83
     came
    -1.83
    POSITIVE LOGITS
    ↵↵
    2.38
    俢
    2.28
    often
    2.00
     exceedingly
    1.93
    厹
    1.84
    usually
    1.80
     COULD
    1.80
    では
    1.73
     forne
    1.73
    geladen
    1.72
    Activations Density 0.006%

    No Known Activations