© 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. 128094
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on occurrences of the substring “min” (as in minimum‐value parameters or “min” range indicators).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    minimum or start

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     soggetto
    -1.01
     небольшие
    -0.96
     anschließend
    -0.94
     integri
    -0.93
    ändigkeit
    -0.90
     неболь
    -0.88
     Verf
    -0.88
    还在
    -0.88
    达成
    -0.87
    お客
    -0.85
    POSITIVE LOGITS
     and
    1.13
     Minimum
    1.08
    心底
    1.07
    城主
    0.95
     zeg
    0.91
     sû
    0.91
     animado
    0.91
    setMinimum
    0.91
     resmi
    0.90
     minValue
    0.90
    Activations Density 0.015%

    No Known Activations