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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58742
    Prev
    Next
    INDEX
    Explanations

    API key in URLs

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

    The neuron fires on numeric tokens—i.e. sequences of digits (often in URLs, IDs, or counts).

    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
    思います
    -0.78
    لبية
    -0.75
    scri
    -0.70
    してきました
    -0.69
     Scri
    -0.68
     Scramble
    -0.68
    觴
    -0.68
    かない
    -0.68
    leck
    -0.68
    サリー
    -0.65
    POSITIVE LOGITS
    ին
    0.92
    requested
    0.82
    drück
    0.80
     irland
    0.78
    initialization
    0.77
     plasmid
    0.75
    鹿
    0.75
    RAZ
    0.75
     ditto
    0.74
     Requested
    0.74
    Activations Density 0.008%

    No Known Activations