© 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. 28
    Prev
    Next
    INDEX
    Explanations

    mean +/- SD or SEM

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

    The neuron fires on numeric measurement tokens (e.g. means, SDs, counts)—i.e. statistical or quantitative values.

    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
     муки
    -0.93
    льність
    -0.91
    umbria
    -0.87
    ificacion
    -0.85
    Cevap
    -0.85
     ufficiali
    -0.84
    InitVars
    -0.83
    liehen
    -0.82
    ният
    -0.81
    ГЛА
    -0.81
    POSITIVE LOGITS
     that
    0.98
     always
    0.92
    ummings
    0.90
    Suppress
    0.87
    あくまで
    0.87
    濤
    0.83
     ͜
    0.82
    ことも
    0.82
     marzo
    0.82
     how
    0.82
    Activations Density 0.021%

    No Known Activations