© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1249
    Prev
    Next
    INDEX
    Explanations

    code structure initialization

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

    The neuron fires on numeric tokens (digit sequences) 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
    absolutely
    -1.14
     áng
    -1.04
    perhaps
    -1.02
    いただきたい
    -1.01
    certainly
    -1.00
     záz
    -0.98
     lì
    -0.97
     lã
    -0.97
     naší
    -0.97
     cóc
    -0.96
    POSITIVE LOGITS
    Some
    1.17
    You
    1.16
    Ｗ
    1.15
    The
    1.13
    An
    1.12
     This
    1.11
     rudimentary
    1.09
    Ἄ
    1.09
     people
    1.07
     Some
    1.05
    Activations Density 0.077%

    No Known Activations