© 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. 64035
    Prev
    Next
    INDEX
    Explanations

    Bay of Pigs Operations

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

    The neuron activates on numeric tokens (e.g. standalone numbers such as years, Version numbers, amounts, or other digit sequences).

    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
     nogen
    -0.74
     Serrano
    -0.73
    typing
    -0.73
    liac
    -0.72
     اینترنتی
    -0.71
     about
    -0.70
    colari
    -0.70
    lagt
    -0.69
    лаш
    -0.69
     peligros
    -0.68
    POSITIVE LOGITS
    sunter
    0.73
     zvyš
    0.66
     ถูก
    0.65
     campañas
    0.65
    も見
    0.63
    inguished
    0.63
    phyr
    0.63
    hup
    0.63
    inigungs
    0.61
    やう
    0.60
    Activations Density 0.042%

    No Known Activations