© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101748
    Prev
    Next
    INDEX
    Explanations

    shape, steep, shear

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

    The neuron activates on technical measurement and parameter terms (e.g. “shape,” “height,” “skewness,” “kurtosis,” “location,” “slope”) often paired with numeric values in scientific contexts.

    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
     sebaik
    -1.59
    unno
    -1.58
    zembro
    -1.57
    gradable
    -1.54
    ING
    -1.53
    брь
    -1.49
    datable
    -1.48
     Ellos
    -1.45
    锲
    -1.45
    anted
    -1.44
    POSITIVE LOGITS
     in
    1.80
     beginning
    1.63
     first
    1.61
     throughout
    1.48
     through
    1.45
     even
    1.44
     the
    1.40
     on
    1.39
     each
    1.33
     perhaps
    1.33
    Activations Density 0.032%

    No Known Activations