© 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. 34-GEMMASCOPE-RES-131K
    7. 117186
    Prev
    Next
    INDEX
    Explanations

    formal announcements and results

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

    This neuron detects numeric tokens (sequences of digits) in the text.

    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
    ümüş
    -0.76
    orse
    -0.67
    RAL
    -0.66
     supervis
    -0.66
    вах
    -0.65
     बढ़
    -0.65
    CCL
    -0.65
    impose
    -0.65
    Então
    -0.63
     Vern
    -0.62
    POSITIVE LOGITS
    就好
    0.78
    tał
    0.73
    registry
    0.72
    мә
    0.70
    INATION
    0.68
    Répondre
    0.67
    ctional
    0.67
     attribution
    0.66
    Dil
    0.66
     Scienti
    0.65
    Activations Density 0.076%

    No Known Activations