© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103039
    Prev
    Next
    INDEX
    Explanations

    finding, examined, or assessed

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

    The neuron flags verbs that report experimental evaluation or measurement—e.g. assessed, evaluated, examined, tested, etc.

    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
     некоторы
    -2.11
     baskılı
    -1.84
     hermosos
    -1.78
     Inſ
    -1.77
     dekoratif
    -1.75
     refroid
    -1.65
     çanta
    -1.63
     ſie
    -1.62
    굼
    -1.60
     rénovation
    -1.59
    POSITIVE LOGITS
     in
    1.73
     of
    1.66
     via
    1.64
     showed
    1.52
     through
    1.52
    Apesar
    1.42
     without
    1.42
    день
    1.40
     while
    1.38
     whilst
    1.35
    Activations Density 0.327%

    No Known Activations