© 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. 116326
    Prev
    Next
    INDEX
    Explanations

    URLs and links

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

    The neuron detects tokens composed primarily of digits (i.e. numeric sequences).

    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
     dör
    -0.81
    tü
    -0.77
    fotografie
    -0.75
     kroner
    -0.75
     kari
    -0.74
    kmeans
    -0.74
     avoidable
    -0.73
    IIII
    -0.73
     Î
    -0.72
    isNumber
    -0.72
    POSITIVE LOGITS
     СССР
    0.72
     getResult
    0.71
    </tbody>
    0.68
    業務
    0.65
    terminated
    0.65
     manifested
    0.64
     Begle
    0.63
    May
    0.63
     kapcsol
    0.63
    spawn
    0.63
    Activations Density 0.056%

    No Known Activations