© 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. 10-GEMMASCOPE-RES-131K
    7. 85462
    Prev
    Next
    INDEX
    Explanations

    log4j, twitter4j, Neo4j

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

    This neuron activates on tokens that are technology or library names featuring the digit “4” (e.g. twitter4j, Neo4j, PETSc C4py, D4R).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    뮐
    -2.30
    Ꮸ
    -2.27
    linawan
    -2.20
    媼
    -2.13
    🪆
    -2.11
    汌
    -2.09
    mpagne
    -2.09
    оргаш
    -2.06
    харш
    -2.05
    侥
    -2.02
    POSITIVE LOGITS
    In
    3.19
    x
    2.94
    nt
    2.59
    4
    2.42
    ?
    2.41
    r
    2.27
    ft
    2.23
    in
    2.13
    io
    2.11
    For
    2.11
    Activations Density 0.015%

    No Known Activations