© 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. 15208
    Prev
    Next
    INDEX
    Explanations

    P.A.D

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

    The neuron fires on tokens that consist of one or more letters immediately followed by a period and a sequence of digits (e.g. “O.1272,” “P.968”).

    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
    を
    -2.66
    が
    -2.27
    は
    -2.19
    も
    -2.09
    があり
    -1.94
    などが
    -1.88
    で
    -1.82
    などを
    -1.80
    方針
    -1.80
    と
    -1.77
    POSITIVE LOGITS
    為に
    2.50
    ようですが
    1.92
    様な
    1.84
    たびに
    1.79
    気がする
    1.75
    ところに
    1.74
    N
    1.73
    ようで
    1.68
    ようになって
    1.68
    ようになります
    1.63
    Activations Density 0.073%

    No Known Activations