© 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. 22-GEMMASCOPE-RES-131K
    7. 27063
    Prev
    Next
    INDEX
    Explanations

    two other groups

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

    The neuron detects instances of the number “two” (the spelled‐out count) 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_22/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
     duality
    -0.93
     that
    -0.91
     полови
    -0.89
     viime
    -0.87
    Dual
    -0.85
     eleven
    -0.85
    憬
    -0.83
     eight
    -0.82
    арт
    -0.82
     große
    -0.81
    POSITIVE LOGITS
     other
    1.66
     thirds
    1.27
     autres
    1.26
     інших
    1.22
     anderen
    1.20
     других
    1.16
     остальные
    1.16
    other
    1.13
     innych
    1.12
     others
    1.11
    Activations Density 0.077%

    No Known Activations