© 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. 115734
    Prev
    Next
    INDEX
    Explanations

    calculate probability of picking

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

    The neuron fires on numeric literal tokens (stand-alone digits or numbers) in mathematical expressions.

    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
    Another
    -1.36
    ܜ
    -1.22
     another
    -1.19
    Some
    -1.17
    Probably
    -1.17
     That
    -1.12
    Maybe
    -1.11
     Obviously
    -1.10
    Many
    -1.09
    Obviously
    -1.08
    POSITIVE LOGITS
    などを
    1.11
    .'-
    1.09
    flats
    1.05
     وت
    1.05
    #
    1.02
     pán
    1.02
    "..
    1.02
    "--
    1.02
    ,-.
    1.01
    --.
    1.00
    Activations Density 0.029%

    No Known Activations