© 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. 58612
    Prev
    Next
    INDEX
    Explanations

    licenses and image terms

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

    This neuron is highly tuned to bits of formal licensing or disclaimer boilerplate (terms like “License,” “Agreement,” “User expressly acknowledges and agrees,” copyright/license headers, etc.).

    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
     RSSSF
    -0.95
     filmed
    -0.91
    uberge
    -0.90
     vidéos
    -0.84
     劇場
    -0.81
     пев
    -0.80
    MEASURE
    -0.80
    EntityType
    -0.79
     screenshots
    -0.79
    ऐ
    -0.79
    POSITIVE LOGITS
     galleries
    1.30
     cropping
    1.25
     gallery
    1.25
     photographer
    1.24
     photographers
    1.23
     Lightroom
    1.20
     Kodak
    1.19
     captions
    1.17
     Photographer
    1.12
    exif
    1.08
    Activations Density 0.059%

    No Known Activations