© 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. 34-GEMMASCOPE-RES-131K
    7. 64709
    Prev
    Next
    INDEX
    Explanations

    license that or provided that

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

    The neuron strongly activates on comment lines that reference licensing or copyright terms (e.g. “license”) in source‐code headers.

    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
     quartiere
    -0.68
    Amanda
    -0.68
     nukes
    -0.67
    Välkommen
    -0.67
    ámico
    -0.66
    ptes
    -0.66
    えている
    -0.65
     nắp
    -0.65
     Abor
    -0.63
     Amts
    -0.63
    POSITIVE LOGITS
    that
    2.33
     that
    2.27
    That
    2.17
    THAT
    2.11
     THAT
    2.03
     That
    2.02
     که
    1.42
    が
    1.41
     που
    1.40
    thats
    1.38
    Activations Density 0.120%

    No Known Activations