© 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. 22-GEMMASCOPE-RES-131K
    7. 14540
    Prev
    Next
    INDEX
    Explanations

    adding to arrays and lists

    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
     كافة
    -1.07
     part
    -1.05
     /
    -1.05
     am
    -1.04
     etc
    -1.04
     sent
    -1.03
     use
    -1.03
     are
    -1.02
    thodoxy
    -1.02
    ^*
    -1.02
    POSITIVE LOGITS
     предлагает
    1.18
    Då
    1.17
    Év
    1.15
    Nyt
    1.09
    sana
    1.09
    Väl
    1.08
     quizás
    1.06
     Uniwers
    1.04
    Tapi
    1.04
     rús
    1.04
    Activations Density 0.001%

    No Known Activations