© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112794
    Prev
    Next
    INDEX
    Explanations

    all types

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

    The neuron strongly activates on occurrences of the word “all.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     utilizando
    -1.95
    羕
    -1.94
     navegando
    -1.84
     verdieping
    -1.76
     vollständig
    -1.73
    וּ
    -1.71
    uties
    -1.68
    '';
    -1.63
    はじ
    -1.63
     tn
    -1.60
    POSITIVE LOGITS
     who
    2.28
    r
    2.22
    OCOLATE
    2.13
     that
    2.11
     användas
    1.98
     (
    1.87
     finnas
    1.82
     said
    1.82
     したい
    1.81
     désol
    1.80
    Activations Density 0.016%

    No Known Activations