© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64411
    Prev
    Next
    INDEX
    Explanations

    r code assignments and vector creations

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

    The neuron detects numeric literals (tokens representing numbers).

    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
     Cricket
    -0.84
     cucharadas
    -0.82
    lrrrr
    -0.78
    counted
    -0.77
    ⲣ
    -0.76
     Chit
    -0.75
     scopri
    -0.74
    сколь
    -0.71
     Cel
    -0.71
    Cooldown
    -0.71
    POSITIVE LOGITS
     c
    5.34
    c
    3.44
    ｃ
    2.25
    𝑐
    1.75
     C
    1.74
    ℅
    1.63
     с
    1.51
    setC
    1.35
    C
    1.34
    с
    1.23
    Activations Density 0.157%

    No Known Activations