© 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. 22-GEMMASCOPE-RES-131K
    7. 128238
    Prev
    Next
    INDEX
    Explanations

    must be

    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
    Forrás
    -1.32
    Unternehmen
    -1.25
    дной
    -1.25
     dificil
    -1.23
    牁
    -1.21
     magari
    -1.20
     unangemessene
    -1.20
    abatic
    -1.14
    foundland
    -1.13
     whatnot
    -1.13
    POSITIVE LOGITS
    安い
    1.34
     be
    1.30
    素晴らしい
    1.29
     国际
    1.24
     莫
    1.17
     国家
    1.16
     纳
    1.13
    toronto
    1.13
     Progression
    1.10
    charlie
    1.10
    Activations Density 0.027%

    No Known Activations