© 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. 31112
    Prev
    Next
    INDEX
    Explanations

    iteration and counting

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

    The neuron activates on numeric literals (digits and small number constants) in 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
     zero
    -1.00
    ZERO
    -0.99
    Specifik
    -0.95
    motorola
    -0.95
     two
    -0.91
    ấ
    -0.90
     Zero
    -0.84
    Zero
    -0.84
     zéro
    -0.83
    vės
    -0.82
    POSITIVE LOGITS
     contando
    0.81
    haf
    0.81
     Alek
    0.79
    neum
    0.77
     <=
    0.77
    leq
    0.76
    leqslant
    0.75
    ]<<"
    0.75
    uwa
    0.73
    ългария
    0.73
    Activations Density 0.019%

    No Known Activations