© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68581
    Prev
    Next
    INDEX
    Explanations

    CSS units and selectors

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

    The neuron fires on numeric measurement tokens (e.g. lengths, margins, paddings) and their units (px, em, dp, 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_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
     into
    -1.15
     to
    -1.05
     zufried
    -0.98
    tshire
    -0.97
    porsche
    -0.96
    mice
    -0.96
     zonder
    -0.95
    cets
    -0.95
     zijne
    -0.93
     tijdens
    -0.92
    POSITIVE LOGITS
     pescado
    0.91
     JULIO
    0.89
    рыв
    0.86
     before
    0.83
     romanos
    0.82
    cestry
    0.81
    フィ
    0.80
     레
    0.79
     escri
    0.79
    ously
    0.79
    Activations Density 0.002%

    No Known Activations