© 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. 86808
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinals

    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
     prega
    -1.24
     its
    -1.22
    有种
    -1.21
    过年
    -1.21
     brill
    -1.20
     Inſ
    -1.20
     zile
    -1.20
     masina
    -1.20
     brillant
    -1.19
    ",
    -1.18
    POSITIVE LOGITS
     ohnehin
    1.58
    睡眠
    1.44
     of
    1.36
    mohon
    1.35
     tierras
    1.32
     của
    1.28
     ejemplar
    1.27
     heiß
    1.26
     Verhältnis
    1.25
     stattfinden
    1.25
    Activations Density 0.066%

    No Known Activations