© 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. 15489
    Prev
    Next
    INDEX
    Explanations

    so much, so many

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

    The neuron is tuned to pick up on degree-adverb modifiers or “intensifiers” (words like “so,” “quite,” and “just”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     in
    -1.56
    camisetas
    -1.53
    魮
    -1.49
     casó
    -1.49
    ardı
    -1.47
    𓋼
    -1.45
    ſſel
    -1.44
     polícia
    -1.43
    珢
    -1.41
     luy
    -1.41
    POSITIVE LOGITS
    T
    1.58
    r
    1.57
    '
    1.53
    ‌.
    1.52
    er
    1.52
    p
    1.49
    v
    1.46
    ar
    1.44
    al
    1.43
    h
    1.43
    Activations Density 0.034%

    No Known Activations