© 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. 34-GEMMASCOPE-RES-131K
    7. 91502
    Prev
    Next
    INDEX
    Explanations

    local maxima and minima

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

    The neuron activates on terms referring to optimization critical points—especially “local” paired with “minimum” or “maximum” (and related loss‐landscape jargon).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Olga
    -0.80
     Tapes
    -0.79
     rango
    -0.76
     fono
    -0.73
     tapes
    -0.72
     Caixa
    -0.71
     semp
    -0.71
    timeScale
    -0.71
    期間限定
    -0.69
     falcon
    -0.69
    POSITIVE LOGITS
     maxima
    3.25
     minima
    3.08
     maximum
    2.86
     minimum
    2.75
    maximum
    2.33
     Maxima
    2.33
    Maximum
    2.23
    minimum
    2.22
     max
    2.03
    Minimum
    2.03
    Activations Density 0.079%

    No Known Activations