© 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. 10-GEMMASCOPE-RES-131K
    7. 69108
    Prev
    Next
    INDEX
    Explanations

    don't know why

    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_10/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
     and
    -1.51
     всех
    -1.30
     “
    -1.26
    ↵↵
    -1.17
     of
    -1.17
    upt
    -1.15
    siel
    -1.11
    mphs
    -1.07
     ''
    -1.05
    クリーム
    -1.03
    POSITIVE LOGITS
     two
    1.45
     felice
    1.26
     various
    1.21
     it
    1.21
     three
    1.20
    Gön
    1.19
     vantaggio
    1.17
    Vlastnosti
    1.17
    Výhody
    1.16
    兩種
    1.13
    Activations Density 0.114%

    No Known Activations