© 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. 69023
    Prev
    Next
    INDEX
    Explanations

    user license agreement

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

    This neuron detects tokens that are dates, numbers, or other named‐entity terms (e.g. proper nouns).

    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
    !」
    -0.99
     tuo
    -0.98
     tenis
    -0.98
     coreano
    -0.97
    ी
    -0.93
     parlamento
    -0.93
     fotografi
    -0.92
     reng
    -0.90
     I
    -0.89
     Golfo
    -0.89
    POSITIVE LOGITS
     shall
    1.19
     powinna
    1.09
    să
    1.05
     kennis
    1.02
     prijzen
    1.02
     disminuir
    1.01
    にい
    0.96
     ktorá
    0.96
     môžu
    0.96
    pshire
    0.95
    Activations Density 0.022%

    No Known Activations