© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111556
    Prev
    Next
    INDEX
    Explanations

    start of descriptive phrases or code

    np_acts-logits-general · gemini-2.5-flash-lite

    text describing locations, distances, and spatial relationships in accommodation or venue descriptions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    illants
    -1.38
     nästan
    -1.34
    txt
    -1.34
     samtidigt
    -1.30
     tehdä
    -1.28
    uluş
    -1.27
    Kelebihan
    -1.22
     (
    -1.21
    孤独
    -1.19
     auttaa
    -1.19
    POSITIVE LOGITS
     including
    1.56
     that
    1.54
     in
    1.39
     where
    1.38
     of
    1.34
     a
    1.26
     acesta
    1.23
     成人
    1.23
     termurah
    1.23
     posiada
    1.23
    Activations Density 0.052%

    No Known Activations