© 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. 10-GEMMASCOPE-RES-131K
    7. 14859
    Prev
    Next
    INDEX
    Explanations

    normal or usual states

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

    The neuron activates on adverbs and adjectives that indicate typicality or frequency—words like “usually,” “normally,” “common,” “general(ly),” and “daily.”

    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
     verdaderamente
    -1.59
    暎
    -1.53
    osob
    -1.52
    lja
    -1.52
    plakat
    -1.50
     disfru
    -1.47
     respald
    -1.47
     Canadá
    -1.47
    CALENDAR
    -1.47
    soal
    -1.46
    POSITIVE LOGITS
    y
    1.94
    de
    1.85
    me
    1.84
    m
    1.84
    d
    1.83
    st
    1.80
    will
    1.80
    o
    1.80
    w
    1.76
    これを
    1.64
    Activations Density 0.008%

    No Known Activations