© 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. 41742
    Prev
    Next
    INDEX
    Explanations

    strength and intensity

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

    The neuron fires on occurrences of the root “vigor,” e.g. the adjectives “vigorous” and adverbs like “vigorously.”

    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
     decidedly
    -2.92
     immense
    -2.92
     predominantly
    -2.86
    I
    -2.86
     ridiculously
    -2.84
     tremendous
    -2.81
     incredibly
    -2.80
     unbelievably
    -2.77
     insanely
    -2.77
     amazingly
    -2.75
    POSITIVE LOGITS
    While
    2.53
    Only
    2.47
    Even
    2.45
    Surprisingly
    2.44
     If
    2.42
     While
    2.42
     Although
    2.30
    There
    2.30
    Quite
    2.30
    Although
    2.28
    Activations Density 0.003%

    No Known Activations