© 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. 58454
    Prev
    Next
    INDEX
    Explanations

    detector stations

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

    This neuron detects C/C++ `#include` directives specifying header file paths (especially quoted file paths with slashes and dots).

    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
     vertex
    -0.81
    CompleteListener
    -0.79
    Tracks
    -0.79
    大家好
    -0.74
    oche
    -0.74
    ར་བ
    -0.73
    vertex
    -0.73
    bsp
    -0.71
     elliptic
    -0.71
    ärna
    -0.71
    POSITIVE LOGITS
     Chamber
    0.96
    Chamber
    0.94
    GEM
    0.88
     chamber
    0.85
     chambers
    0.82
     hits
    0.79
     GEM
    0.77
     Chambers
    0.77
     strips
    0.76
     stations
    0.74
    Activations Density 0.014%

    No Known Activations