© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55693
    Prev
    Next
    INDEX
    Explanations

    logistic, regression, and Cox analysis

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

    The neuron activates on numeric tokens and figures (e.g. counts, percentages, and other numerical values).

    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
     SOLD
    -0.80
    structors
    -0.78
     Altos
    -0.76
     smer
    -0.73
    鞨
    -0.72
     behand
    -0.72
     pimienta
    -0.71
     Estimation
    -0.70
     semble
    -0.70
     TREATMENT
    -0.69
    POSITIVE LOGITS
     multivariate
    1.58
     adjusted
    1.58
     logistic
    1.38
     multi
    1.34
    Adjusted
    1.28
    adjusted
    1.23
     univ
    1.20
     Adjusted
    1.20
     adjusting
    1.17
     Logistic
    1.17
    Activations Density 0.164%

    No Known Activations