© 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. 34-GEMMASCOPE-RES-131K
    7. 90689
    Prev
    Next
    INDEX
    Explanations

    played counts or quantities

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

    The neuron responds to numeric tokens—digits or multi‐digit numbers (e.g. counts, ratings, years).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    dieu
    -0.82
    倒是
    -0.81
     maar
    -0.81
    ørn
    -0.81
     gorra
    -0.79
     probado
    -0.79
    тились
    -0.79
     Ciebie
    -0.79
     geprüft
    -0.79
    Het
    -0.79
    POSITIVE LOGITS
     by
    1.05
    このように
    0.90
    Still
    0.85
    EMPO
    0.80
     trustworthy
    0.79
    Such
    0.79
    LLA
    0.79
    kolog
    0.78
     DCM
    0.77
    まだ
    0.76
    Activations Density 0.005%

    No Known Activations