© 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. 33427
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

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

    This neuron detects C/C++ preprocessor include directives (the header filenames inside `#include "…"`).

    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
     anonim
    -1.17
     Audiodateien
    -1.13
     Issus
    -1.11
    ⸼
    -1.07
     insegu
    -1.03
    malink
    -1.02
     può
    -1.02
     pathway
    -0.98
    ıştır
    -0.98
     precin
    -0.98
    POSITIVE LOGITS
    Several
    0.98
     сала
    0.96
    íguez
    0.96
    ᶰ
    0.96
     сезо
    0.94
     they
    0.93
     =>'
    0.91
    ranslated
    0.91
    gameserver
    0.91
    НГ
    0.89
    Activations Density 0.023%

    No Known Activations