© 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. 71669
    Prev
    Next
    INDEX
    Explanations

    graduated, degrees, university

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

    The neuron selectively activates on numeric tokens denoting calendar years (four-digit date figures) in biographical texts.

    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
     wciąż
    -1.71
     they
    -1.70
    滹
    -1.67
     deliciosos
    -1.63
     that
    -1.62
     offrire
    -1.60
     produrre
    -1.59
    彼らは
    -1.59
     fornire
    -1.57
    隄
    -1.54
    POSITIVE LOGITS
     consequent
    1.39
     связан
    1.38
     «
    1.36
     '',
    1.35
    куртка
    1.34
     ,,
    1.29
    StreetMap
    1.27
                
    1.25
     \
    1.23
    の場合
    1.22
    Activations Density 0.118%

    No Known Activations