© 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. 2810
    Prev
    Next
    INDEX
    Explanations

    . followed by dot

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

    The neuron detects standalone numeric tokens (i.e. integer constants).

    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
     each
    -0.86
    جلس
    -0.85
    stages
    -0.84
    kanı
    -0.83
     morning
    -0.82
    acon
    -0.81
     member
    -0.81
    achu
    -0.80
    нечно
    -0.79
     here
    -0.78
    POSITIVE LOGITS
    的位置
    1.04
    eafter
    1.02
     pos
    0.99
     separación
    0.94
     찾
    0.93
     לאחר
    0.93
     closing
    0.92
     end
    0.91
    の位置
    0.89
    begins
    0.89
    Activations Density 0.018%

    No Known Activations