© 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. 78599
    Prev
    Next
    INDEX
    Explanations

    derive, use, clone, copy, debug

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

    The neuron detects numeric tokens (digits and numbers) in code or text.

    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
     stolet
    -0.82
     چرم
    -0.77
    URIDAD
    -0.76
    نامج
    -0.75
     lucre
    -0.74
    dirond
    -0.74
     DKK
    -0.73
    Espèce
    -0.72
     IPT
    -0.72
     REI
    -0.71
    POSITIVE LOGITS
    Debug
    1.29
     Clone
    1.17
    Clone
    1.14
     clone
    1.02
     Copy
    0.96
     debug
    0.94
     Debug
    0.93
    Copy
    0.92
    接下来
    0.87
     copy
    0.85
    Activations Density 0.003%

    No Known Activations