© 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. 73177
    Prev
    Next
    INDEX
    Explanations

    comment headers or "gardner"

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

    The neuron is strongly activated by occurrences of the variable name “userInput” (i.e. references to that Scanner‐style identifier).

    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
    鋇
    -3.22
    踽
    -2.73
    ！"
    -2.67
     idée
    -2.63
    淩
    -2.55
    原神
    -2.44
    糅
    -2.42
    注意事
    -2.41
     soie
    -2.39
    讴
    -2.39
    POSITIVE LOGITS
    a
    3.27
    7
    3.11
    the
    3.08
    8
    3.06
    1
    3.06
    9
    2.91
    6
    2.89
     verhind
    2.72
    4
    2.64
     geleg
    2.44
    Activations Density 0.020%

    No Known Activations