© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 531
    Prev
    Next
    INDEX
    Explanations

    experience or possibility

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

    the presence of adverbs or modal words that express frequency, likelihood, or degree (e.g. often, increasingly, may, typically).

    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
    PENDAHULUAN
    -1.67
     verkoop
    -1.67
     setiap
    -1.57
    vább
    -1.55
    ()]
    -1.55
     cambiado
    -1.49
     sudadera
    -1.48
    荭
    -1.48
     jadx
    -1.48
    aceite
    -1.48
    POSITIVE LOGITS
     use
    1.90
    a
    1.81
    '
    1.73
     '
    1.52
     (
    1.47
    d
    1.42
     "
    1.38
    open
    1.34
    i
    1.34
     also
    1.31
    Activations Density 0.044%

    No Known Activations