© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64377
    Prev
    Next
    INDEX
    Explanations

    message completion or status

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

    The neuron strongly responds to numeric literals (tokens made up of digits).

    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
    zkopf
    -0.72
    adam
    -0.71
    ⲟ
    -0.70
    Subject
    -0.68
    awy
    -0.68
    gido
    -0.67
    Will
    -0.66
     cultured
    -0.65
     viruses
    -0.65
    Gfx
    -0.64
    POSITIVE LOGITS
    paramInt
    0.71
     ريا
    0.69
     mittel
    0.68
    varu
    0.68
    ambig
    0.67
     chóng
    0.66
     Girard
    0.66
    timas
    0.66
     Eraser
    0.66
     siedz
    0.65
    Activations Density 0.062%

    No Known Activations