© 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. 34-GEMMASCOPE-RES-131K
    7. 57861
    Prev
    Next
    INDEX
    Explanations

    @ `include` / `+` specific words

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

    The neuron strongly activates on code‐style tokens—e.g. annotation markers (@), tag prefixes (jsp:), function/module names (manager)—i.e. programming identifiers and symbols.

    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
     all
    -1.45
     more
    -1.40
     their
    -1.32
     what
    -1.32
     or
    -1.28
     with
    -1.26
     on
    -1.23
     both
    -1.23
     over
    -1.20
     from
    -1.19
    POSITIVE LOGITS
     ſol
    1.22
     pè
    1.20
     alpes
    1.12
    wände
    1.12
    튿
    1.11
     BEAUTIFUL
    1.09
     deliciously
    1.09
     CONTIN
    1.09
     jj
    1.07
     ストラップ
    1.06
    Activations Density 0.000%

    No Known Activations