© 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. 99473
    Prev
    Next
    INDEX
    Explanations

    licensed under the License

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

    The neuron is primarily triggered by numeric tokens (strings of digits, e.g. version numbers or line 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
    替换
    -0.75
    coop
    -0.69
    κολου
    -0.66
     postav
    -0.66
    っていると
    -0.65
     Volk
    -0.65
    verton
    -0.65
    ⵎ
    -0.65
    itti
    -0.63
    esub
    -0.63
    POSITIVE LOGITS
     تولید
    0.73
    Andres
    0.72
    dfn
    0.70
    Ǻ
    0.70
    anças
    0.66
    串
    0.66
     küçük
    0.66
     carbonic
    0.65
     Scheme
    0.64
     SDA
    0.64
    Activations Density 0.076%

    No Known Activations