© 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. 58594
    Prev
    Next
    INDEX
    Explanations

    metadata or author

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

    The neuron fires on the “/” token in C preprocessor include paths, especially in “linux/…” header file references.

    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
     Urqu
    -0.75
     Comeback
    -0.70
    Serde
    -0.70
     Vard
    -0.68
     Lipid
    -0.68
     deple
    -0.68
    HIP
    -0.67
    tetten
    -0.67
    áním
    -0.67
     IMPLICATIONS
    -0.66
    POSITIVE LOGITS
    𝓴
    0.68
    tvguide
    0.65
    caine
    0.63
    kka
    0.63
     randint
    0.62
     Cai
    0.62
    ouc
    0.62
    蟒
    0.62
     Eg
    0.61
     geraten
    0.61
    Activations Density 0.101%

    No Known Activations