© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7018
    Prev
    Next
    INDEX
    Explanations

    probability questions containing letters

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

    The neuron fires on numeric literals—tokens made up of digits (including numbers in prose and character‐literal digits in code).

    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
    umme
    -1.12
    ഢ
    -1.09
    ControllerAdvice
    -1.07
    hlar
    -1.06
    lösen
    -1.05
    DAOImpl
    -1.04
    rester
    -1.03
    pergillus
    -1.02
     dátum
    -1.02
    entuk
    -1.02
    POSITIVE LOGITS
    u
    1.02
     ,.
    1.01
     unterschied
    0.96
     a
    0.93
     दोनों
    0.92
    o
    0.87
    就是在
    0.86
     I
    0.85
    A
    0.85
    の特徴
    0.84
    Activations Density 0.034%

    No Known Activations