© 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. 71212
    Prev
    Next
    INDEX
    Explanations

    state names and programming identifiers

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

    This neuron strongly activates on code identifiers or tokens that include digits (e.g. variable names ending in numbers).

    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
     of
    -1.23
    ceptre
    -1.11
     for
    -1.09
     Preisen
    -1.02
     mereka
    -0.96
     R
    -0.94
     Egyes
    -0.93
     N
    -0.92
     M
    -0.89
    rids
    -0.89
    POSITIVE LOGITS
    alucía
    1.19
     GEORGIA
    1.17
    >>>>
    1.15
    felf
    1.10
    >>>>>>
    1.08
     VIRGINIA
    1.08
    melons
    1.08
    entown
    1.05
     FRANC
    1.02
     ARIZONA
    1.02
    Activations Density 0.016%

    No Known Activations