© 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. 22-GEMMASCOPE-RES-131K
    7. 33415
    Prev
    Next
    INDEX
    Explanations

    public code declarations

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

    The neuron activates on access‐modifier keywords (e.g. “public”, “private”) in code declarations.

    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
     with
    -1.34
     after
    -1.34
     other
    -1.33
     while
    -1.27
     various
    -1.25
     several
    -1.20
     another
    -1.20
     from
    -1.20
     more
    -1.17
     when
    -1.16
    POSITIVE LOGITS
     alltid
    1.09
     lác
    1.08
     quí
    1.07
     áng
    1.05
     Vl
    1.04
     Notting
    1.03
     تنها
    1.02
    ⅕
    1.02
     bát
    1.01
     nécess
    1.00
    Activations Density 0.007%

    No Known Activations