© 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. 47584
    Prev
    Next
    INDEX
    Explanations

    evaluations of quality or performance

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

    The neuron strongly activates on numeric tokens (multi‐digit numbers such as years, statistics, measurements, or identifiers).

    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
     qualità
    -0.73
     Benefits
    -0.70
    Benefits
    -0.66
    ربية
    -0.65
    sore
    -0.64
     prawda
    -0.64
    garn
    -0.64
    zg
    -0.63
     espectador
    -0.63
    ocuk
    -0.63
    POSITIVE LOGITS
     satisfactory
    4.31
     unsatisfactory
    3.34
    atisfactory
    2.94
     satisf
    2.69
     satisfactorily
    2.63
     satisfying
    2.56
     Satis
    2.48
    satis
    2.41
     удовлет
    2.38
     satisfa
    2.30
    Activations Density 0.089%

    No Known Activations