© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5451
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric expressions or measurements (e.g. scores, percentages, scales, statistics).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     కథ
    0.66
     引き
    0.66
    InMemory
    0.63
    砟
    0.59
    <unused36>
    0.58
     लर्न
    0.58
     igény
    0.58
    莢
    0.56
    चन
    0.56
     Habe
    0.55
    POSITIVE LOGITS
     rating
    2.08
    评分
    2.08
     ratings
    1.96
     grading
    1.88
     score
    1.84
     Rating
    1.82
     scoring
    1.80
    Rating
    1.77
     평가
    1.77
    評価
    1.72
    Activations Density 0.736%

    No Known Activations