© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44219
    Prev
    Next
    INDEX
    Explanations

    sports contract financial details

    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
     other
    -1.26
     its
    -1.23
    ・・。
    -1.21
     rezultat
    -1.20
    元々
    -1.20
    未だ
    -1.19
    坚决
    -1.16
    ouncements
    -1.15
     Allowing
    -1.15
     institucional
    -1.14
    POSITIVE LOGITS
     waarschijnlijk
    1.21
     mungkin
    1.20
    ikuti
    1.20
     or
    1.17
     ۲۰۱
    1.16
    correre
    1.16
     you
    1.14
    DAM
    1.13
     moeili
    1.13
     komende
    1.12
    Activations Density 0.027%

    No Known Activations