© 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. 35420
    Prev
    Next
    INDEX
    Explanations

    Teresa Carlson

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

    This neuron detects C/C++ include‐directive tokens (headers and the surrounding punctuation in `#include` lines).

    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
     from
    -1.23
     varit
    -1.06
     éter
    -1.05
    liath
    -1.04
    .../
    -1.00
     silueta
    -1.00
    gebouw
    -0.99
     ImageView
    -0.99
    Čes
    -0.99
     TextView
    -0.98
    POSITIVE LOGITS
     eingeladen
    1.17
    原本
    1.05
    に戻る
    1.03
    杈
    0.97
     zwłaszcza
    0.96
     будут
    0.94
     kwiaty
    0.91
    好像
    0.91
     debido
    0.90
     Defines
    0.90
    Activations Density 0.000%

    No Known Activations