© 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. 65006
    Prev
    Next
    INDEX
    Explanations

    mask or clipping

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

    This neuron selectively activates on graphic‐design and image‐editing terminology—software names (e.g. Illustrator, CSS), operations (rounded corners, masking), and related UI elements (header, logo).

    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
    affirm
    -0.77
     Anch
    -0.70
    lierte
    -0.69
    anch
    -0.68
     Haram
    -0.66
    iar
    -0.66
    jwt
    -0.65
    Économie
    -0.65
     coach
    -0.65
    ahren
    -0.65
    POSITIVE LOGITS
     clipping
    1.69
     mask
    1.42
    mask
    1.42
     clip
    1.36
     Cli
    1.34
    clip
    1.31
    Cli
    1.26
     clipped
    1.26
    Clip
    1.22
    Mask
    1.20
    Activations Density 0.059%

    No Known Activations