© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71487
    Prev
    Next
    INDEX
    Explanations

    publisher name following "by"

    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_22/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
     promu
    -1.18
     almohada
    -1.17
     lucr
    -1.16
     Violon
    -1.15
     imedi
    -1.15
     さん
    -1.13
     paloma
    -1.13
     outra
    -1.13
     inne
    -1.12
     byen
    -1.11
    POSITIVE LOGITS
     for
    1.37
     färg
    1.27
    viewpager
    1.23
     on
    1.12
     at
    1.07
     with
    1.01
     francese
    0.99
    توضیحات
    0.99
     The
    0.98
     Peter
    0.97
    Activations Density 0.004%

    No Known Activations