© 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. 117395
    Prev
    Next
    INDEX
    Explanations

    sample size, number, quantity

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

    The neuron activates on mentions of “sample size” (and related sample‐size terms).

    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
     ligue
    -0.84
    Ț
    -0.83
    ográfico
    -0.79
    truck
    -0.78
     taux
    -0.78
    ügel
    -0.77
     rangement
    -0.75
     Theological
    -0.75
     vred
    -0.75
     grá
    -0.73
    POSITIVE LOGITS
     sample
    3.36
     Sample
    2.34
    Sample
    2.31
    sample
    2.28
     SAMPLE
    1.71
    SAMPLE
    1.70
     samples
    1.59
     size
    1.45
    样本
    1.44
    サンプル
    1.31
    Activations Density 0.046%

    No Known Activations