© 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. 39293
    Prev
    Next
    INDEX
    Explanations

    Zal, гу,อา, 谈

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

    The neuron flags tokens containing non-ASCII or special Unicode characters (e.g. letters with diacritics, macrons, Cyrillic/Thai letters, currency symbols).

    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
     preocu
    -2.84
     angene
    -2.83
     alguns
    -2.81
     mezclar
    -2.75
     zahlreichen
    -2.66
    崤
    -2.61
    </b>
    -2.61
     algunos
    -2.56
     identificación
    -2.56
     nightmare
    -2.55
    POSITIVE LOGITS
    $
    2.88
    鼇
    2.72
     tabac
    2.69
    鬭
    2.66
     tramontina
    2.59
    硨
    2.59
    猡
    2.58
     britann
    2.55
    O
    2.52
    ’
    2.50
    Activations Density 0.002%

    No Known Activations