© 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. 3034
    Prev
    Next
    INDEX
    Explanations

    programming output functions

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

    The neuron fires on tokens belonging to output/print statements (e.g. print, printf, System.out.println).

    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
     from
    -1.22
     through
    -1.07
     actually
    -1.05
     directly
    -1.03
     because
    -1.02
     at
    -0.98
     each
    -0.97
     by
    -0.93
     not
    -0.93
     Each
    -0.91
    POSITIVE LOGITS
     "
    1.52
     "\
    1.46
     “
    1.27
    ----------------
    1.21
    ("\
    1.19
    ("
    1.16
     Voici
    1.11
    ****************
    1.10
    ________________
    1.08
     Règlement
    1.03
    Activations Density 0.004%

    No Known Activations