© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28470
    Prev
    Next
    INDEX
    Explanations

    technical specifications and units

    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
    ↵
    -1.43
     vielleicht
    -1.13
     هذه
    -1.13
    :
    -1.09
     этих
    -1.09
    是怎么回事
    -1.09
     they
    -1.08
     الذي
    -1.05
     欣赏
    -1.04
    .”
    -1.03
    POSITIVE LOGITS
     extré
    1.30
    Berat
    1.29
    Gön
    1.25
     bapt
    1.23
    اخته
    1.23
     sés
    1.23
    Makan
    1.21
     Pollut
    1.20
     marbre
    1.17
     tissus
    1.17
    Activations Density 0.000%

    No Known Activations