© 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. 58316
    Prev
    Next
    INDEX
    Explanations

    similar distribution

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

    The neuron is detecting numeric literal tokens (integer and hexadecimal 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
    irnov
    -0.86
    ｔ
    -0.80
    inov
    -0.79
     cero
    -0.77
     دست
    -0.77
    ס
    -0.76
    izumi
    -0.75
    वि
    -0.75
    yorum
    -0.75
    خیص
    -0.75
    POSITIVE LOGITS
    ]._
    0.87
    Auditor
    0.81
    egli
    0.81
     procurando
    0.80
     phiếu
    0.79
    biker
    0.78
    bumper
    0.78
    Livraison
    0.78
    inistro
    0.78
    industan
    0.77
    Activations Density 0.006%

    No Known Activations