© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109249
    Prev
    Next
    INDEX
    Explanations

    c++ stream output <<

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

    The neuron flags standalone numeric tokens (e.g. integer literals or numeric constants) in the code.

    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
    ēju
    -0.94
     rub
    -0.78
    cdnjs
    -0.74
     parç
    -0.71
     Temperatur
    -0.70
     Ich
    -0.70
    醋
    -0.70
     Mejor
    -0.69
     žaid
    -0.69
     Heft
    -0.68
    POSITIVE LOGITS
     <<
    2.97
    <<
    2.16
    <<"
    1.47
    ()<<
    1.39
    )<<
    1.28
    ]<<
    1.27
     <<<
    1.20
    ≪
    1.20
    <<(
    1.03
     >>
    0.96
    Activations Density 0.033%

    No Known Activations