© 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. 22-GEMMASCOPE-RES-131K
    7. 72050
    Prev
    Next
    INDEX
    Explanations

    governing permissions

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

    The neuron strongly activates on license‐and‐disclaimer boilerplate terms (e.g. “liable,” “dealings,” “governing,” “limitations”) in code comments.

    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
    wiches
    -1.29
    RRRR
    -1.27
    vertising
    -1.24
    iiiii
    -1.23
    cll
    -1.18
    ooooooo
    -1.18
    ől
    -1.18
    mhz
    -1.17
    oooooooooooooooo
    -1.16
    četně
    -1.16
    POSITIVE LOGITS
     of
    1.22
    Kommentare
    1.11
    くださった
    1.09
     but
    0.98
     which
    0.98
    Enregistrer
    0.96
     to
    0.96
    oirs
    0.95
     from
    0.93
    Télécharger
    0.93
    Activations Density 0.044%

    No Known Activations