© 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. 59274
    Prev
    Next
    INDEX
    Explanations

    Newark reminiscing riveting

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

    The neuron fires strongly on words that describe a trance-like, mesmerizing or hypnotic quality.

    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
    4
    -2.59
    ات
    -2.41
     scritta
    -2.27
     electrónica
    -2.06
    at
    -2.06
    6
    -2.05
    은
    -2.02
    ”?
    -1.99
    ad
    -1.98
     Hinblick
    -1.98
    POSITIVE LOGITS
    逦
    2.08
    pM
    2.02
    '
    1.97
    MILLISECONDS
    1.93
     они
    1.90
     first
    1.87
    cinating
    1.86
     ‘‘
    1.85
    TintMode
    1.84
    jící
    1.82
    Activations Density 0.001%

    No Known Activations