© 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. 92515
    Prev
    Next
    INDEX
    Explanations

    license and terms

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

    The neuron fires on legal‐license boilerplate phrasing—e.g. “covered under the terms and conditions” passages in file 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
     Kugel
    -0.77
     erk
    -0.76
     pö
    -0.73
     bö
    -0.73
     lagar
    -0.73
    کند
    -0.72
     espel
    -0.72
    shifts
    -0.71
     brilliant
    -0.71
    icho
    -0.71
    POSITIVE LOGITS
    🦙
    0.84
    日在
    0.84
    inv
    0.80
    gnon
    0.77
    skiej
    0.76
    getL
    0.75
    tta
    0.73
     liturgical
    0.73
     möglichst
    0.72
     Wilk
    0.71
    Activations Density 0.547%

    No Known Activations