© 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. 58139
    Prev
    Next
    INDEX
    Explanations

    minimum

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

    The neuron activates on numeric tokens—literal numbers, digits, and numeric parameter values in markup or code.

    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
    イクアウト
    -0.88
    ོ
    -0.73
    борка
    -0.72
     circa
    -0.70
    嗔
    -0.69
     Leto
    -0.69
    agot
    -0.69
     गा
    -0.69
    iesen
    -0.68
    融入
    -0.68
    POSITIVE LOGITS
    Minimum
    0.92
     getMin
    0.92
     Minimum
    0.89
     Min
    0.88
    minHeight
    0.84
     min
    0.82
    Min
    0.81
    MIN
    0.77
    kelig
    0.74
    minWidth
    0.73
    Activations Density 0.031%

    No Known Activations