© 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. 34094
    Prev
    Next
    INDEX
    Explanations

    code includes and declarations

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

    The neuron fires strongly on programming‐style identifiers, especially CamelCase function and class names (e.g. GUI.DragWindow, MoveRect, BeginVertical, ConnectionWindow) and similar code tokens.

    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
    -1.46
     przechowy
    -1.36
     or
    -1.36
     from
    -1.32
     other
    -1.30
     might
    -1.29
     three
    -1.28
     several
    -1.27
     west
    -1.27
     believes
    -1.27
    POSITIVE LOGITS
     trecho
    1.38
     tabac
    1.30
     convite
    1.30
     ſp
    1.28
     baixar
    1.27
    ступила
    1.26
     esboço
    1.25
     PHARM
    1.24
    ступили
    1.23
     "{\"
    1.20
    Activations Density 0.002%

    No Known Activations