© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27692
    Prev
    Next
    INDEX
    Explanations

    configuration keywords

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

    This neuron activates on CSS color‐setting syntax, especially hex color codes (e.g. “background‐color: #BFD1D4;”).

    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
     felpa
    -1.18
     bobina
    -1.11
    雠
    -1.07
     dezelve
    -1.06
     ciclista
    -1.05
     唯美
    -1.05
     レスト
    -1.05
    삵
    -1.04
     壁紙
    -1.02
    
    -1.02
    POSITIVE LOGITS
     by
    1.22
     with
    1.20
    .(
    1.14
     as
    1.10
     other
    1.09
     any
    1.04
     also
    1.04
    .....
    0.98
    !!!!
    0.98
     "
    0.97
    Activations Density 0.005%

    No Known Activations