© 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. 22-GEMMASCOPE-RES-131K
    7. 14404
    Prev
    Next
    INDEX
    Explanations

    variable assignment or parenthesized expressions

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

    The neuron is selectively activating on numeric literals (numbers) 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_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
     frequentemente
    -1.23
     luscious
    -1.21
     créer
    -1.20
     recente
    -1.16
     joyful
    -1.16
     myriad
    -1.14
     captivating
    -1.12
     dente
    -1.09
     grandiose
    -1.09
     tumultuous
    -1.08
    POSITIVE LOGITS
     at
    1.43
     in
    1.41
     from
    1.27
     (
    1.19
     our
    1.18
     without
    1.18
     one
    1.17
     with
    1.16
     an
    1.12
     spurred
    1.12
    Activations Density 0.001%

    No Known Activations