© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69814
    Prev
    Next
    INDEX
    Explanations

    comparative description

    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
     разные
    -1.53
     mejoras
    -1.48
     adhesivo
    -1.47
     очень
    -1.45
    んでる
    -1.40
     varias
    -1.37
     joyería
    -1.36
    ,”
    -1.34
     felicitación
    -1.34
    ٢
    -1.34
    POSITIVE LOGITS
     to
    2.73
     than
    2.16
     of
    1.47
     that
    1.46
     such
    1.38
     with
    1.32
     and
    1.30
     on
    1.27
     you
    1.21
     against
    1.16
    Activations Density 0.098%

    No Known Activations