© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72180
    Prev
    Next
    INDEX
    Explanations

    footballer who

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

    The neuron activates on numeric tokens—years, volume/page numbers, measurements, and 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_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
    yeri
    -0.83
    øde
    -0.82
    nesto
    -0.82
    gess
    -0.81
    intes
    -0.81
    TOON
    -0.79
     manifolds
    -0.79
    pae
    -0.79
    топ
    -0.79
    scholars
    -0.78
    POSITIVE LOGITS
    istics
    0.81
    帝国
    0.75
    endu
    0.75
    anella
    0.75
    了一個
    0.74
     with
    0.72
    niej
    0.71
     suitable
    0.70
     and
    0.69
    }
    
    0.69
    Activations Density 0.001%

    No Known Activations