© 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. 72662
    Prev
    Next
    INDEX
    Explanations

    Yves, terrier, reciprocating

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

    The neuron is primarily triggered by capitalized proper names (i.e. named entities).

    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
    ↵
    -2.77
     But
    -2.61
    .“
    -2.58
    》。
    -2.48
    》,
    -2.39
    providedIn
    -2.28
     faſt
    -2.14
    回想
    -2.13
    西南
    -2.13
    ”،
    -2.11
    POSITIVE LOGITS
    k
    2.89
    1
    2.81
    ––
    2.80
    t
    2.58
    s
    2.53
    OR
    2.50
    ED
    2.36
    莇
    2.33
    要把
    2.33
    肯定是
    2.33
    Activations Density 0.010%

    No Known Activations