© 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. 57623
    Prev
    Next
    INDEX
    Explanations

    outcome after

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

    The neuron responds strongly to numerical tokens (digits, decimal points, and related punctuation) 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_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
    represented
    -0.90
    performed
    -0.89
    outchou
    -0.88
     Meu
    -0.86
    Ако
    -0.85
    
    -0.85
    FOUND
    -0.84
    唰
    -0.84
    चा
    -0.83
    Лі
    -0.83
    POSITIVE LOGITS
     booking
    0.93
     Promo
    0.89
    átek
    0.86
     guests
    0.82
     gmbh
    0.82
     convention
    0.79
     zab
    0.79
    馥
    0.79
    raa
    0.79
     businessmen
    0.78
    Activations Density 0.009%

    No Known Activations