© 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. 22-GEMMASCOPE-RES-131K
    7. 72978
    Prev
    Next
    INDEX
    Explanations

    nationalities and programming code

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

    The neuron selectively activates on standalone numeric tokens (e.g. section or line numbers).

    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
     our
    -1.10
     stadion
    -1.07
     atmosfer
    -0.94
    cress
    -0.92
    Our
    -0.91
     your
    -0.91
     leher
    -0.88
    Ｌ
    -0.88
     fiume
    -0.88
     mortem
    -0.85
    POSITIVE LOGITS
    ieteur
    1.08
     prič
    1.02
     Geophys
    1.02
     shack
    1.00
     janeiro
    1.00
    iasis
    0.97
    øren
    0.97
    telor
    0.97
    prilis
    0.95
    toare
    0.93
    Activations Density 0.000%

    No Known Activations