© 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. 75470
    Prev
    Next
    INDEX
    Explanations

    just R

    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
     для
    -3.19
    s
    -3.11
     mijn
    -3.03
    e
    -2.94
     моя
    -2.94
    曁
    -2.91
    y
    -2.81
    us
    -2.78
    ၟ
    -2.69
    ꦭ
    -2.69
    POSITIVE LOGITS
    ANIEL
    2.94
    ’
    2.66
     deliciously
    2.48
     famed
    2.45
    ésult
    2.45
    蓐
    2.42
    aI
    2.39
    毟
    2.38
     dando
    2.34
     quintessential
    2.33
    Activations Density 0.022%

    No Known Activations