© 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. 14296
    Prev
    Next
    INDEX
    Explanations

    include stdio

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

    The neuron strongly activates on occurrences of the C header inclusion “#include <stdio.h>.”

    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
    be
    -1.28
     взгляд
    -1.23
     
    -1.23
    AN
    -1.23
    在我们
    -1.21
    r
    -1.20
    她
    -1.16
    L
    -1.14
     "
    -1.13
     [
    -1.12
    POSITIVE LOGITS
    </em>
    1.59
    eadilan
    1.39
     and
    1.39
    ̀
    1.37
    </h3>
    1.37
    icago
    1.32
    猡
    1.30
    cyj
    1.27
    Ꮓ
    1.27
    '')
    1.22
    Activations Density 0.004%

    No Known Activations