© 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. 77935
    Prev
    Next
    INDEX
    Explanations

    first out lesbian

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

    The neuron activates on numeric tokens (numbers and digit sequences) in the 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
     طبی
    -0.85
    顧
    -0.81
     histo
    -0.80
     Venezuela
    -0.78
     HSV
    -0.77
    VOA
    -0.77
     Pogba
    -0.75
     브
    -0.75
    worden
    -0.74
     analogs
    -0.74
    POSITIVE LOGITS
     cod
    0.75
    εύ
    0.74
    coders
    0.72
    iint
    0.71
    diri
    0.71
     автоном
    0.70
    ocities
    0.67
     menjelaskan
    0.66
    痺
    0.66
     estilo
    0.64
    Activations Density 0.011%

    No Known Activations