© 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. 79705
    Prev
    Next
    INDEX
    Explanations

    above a unit

    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
    ⅖
    -1.24
     alkoholu
    -1.23
     素描
    -1.17
     花朵
    -1.16
     ТЕ
    -1.15
     prakti
    -1.13
     kompres
    -1.13
     TextInputType
    -1.12
     花纹
    -1.08
    ſtra
    -1.05
    POSITIVE LOGITS
    :
    1.46
     any
    1.34
     valuable
    1.29
     unique
    1.17
     ideal
    1.15
     when
    1.14
     noteworthy
    1.12
     desirable
    1.10
     substantial
    1.09
     these
    1.05
    Activations Density 0.039%

    No Known Activations