© 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. 22-GEMMASCOPE-RES-131K
    7. 12534
    Prev
    Next
    INDEX
    Explanations

    color

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     logistical
    -1.27
    致力于
    -1.23
     amenazas
    -1.21
     troublesome
    -1.21
    着一个
    -1.20
     there
    -1.20
    ajas
    -1.20
    お昼
    -1.19
     disconcer
    -1.16
    娯
    -1.16
    POSITIVE LOGITS
     of
    2.66
    และ
    1.59
    ЛОВ
    1.41
     colors
    1.34
     color
    1.34
    فت
    1.33
    casal
    1.32
    »,
    1.23
     پروفایل
    1.21
     moft
    1.19
    Activations Density 0.016%

    No Known Activations