© 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. 79627
    Prev
    Next
    INDEX
    Explanations

    programming action verbs

    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
     their
    -1.52
    ⿻
    -1.21
     berikan
    -1.17
     Drž
    -1.17
    TOBER
    -1.17
     páss
    -1.14
     jaka
    -1.13
    ⿳
    -1.13
    tinta
    -1.10
     its
    -1.09
    POSITIVE LOGITS
    AT
    1.12
    ţele
    1.10
     собака
    1.07
     föruts
    1.07
     TAI
    1.04
     собаки
    1.03
    的情绪
    1.00
    錳
    1.00
     //$
    0.98
     Brunei
    0.98
    Activations Density 0.021%

    No Known Activations