© 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. 93268
    Prev
    Next
    INDEX
    Explanations

    Q: prompts and scientific terms

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

    technical and mathematical terminology in academic or scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on technical references to Lyapunov exponents (i.e. exponential separation rates in dynamical systems).

    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
     jeunesse
    -0.80
    حياتها
    -0.73
     dlouho
    -0.71
     Grounds
    -0.69
     Concentration
    -0.69
    Ȃ
    -0.69
    Besch
    -0.66
     வ
    -0.66
    lfloor
    -0.66
     Accumulation
    -0.66
    POSITIVE LOGITS
     Neill
    0.84
     Eylül
    0.75
     dátum
    0.75
     אות
    0.73
    žin
    0.73
    только
    0.72
    analy
    0.71
    pří
    0.71
     synchronize
    0.69
    Pull
    0.69
    Activations Density 0.037%

    No Known Activations