© 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. 15147
    Prev
    Next
    INDEX
    Explanations

    top, left, right positioning

    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
    ле
    -1.25
     such
    -1.16
     including
    -1.11
    なのだ
    -1.10
     his
    -1.08
    出る
    -1.03
     dwie
    -1.03
    ]$,
    -1.02
    ло
    -1.01
     Könige
    -1.00
    POSITIVE LOGITS
    Lá
    1.17
     terceros
    1.16
    inak
    1.09
    Таблица
    1.08
    исленность
    1.06
    hancers
    1.04
    ţin
    1.03
    뿌
    1.02
    Amend
    1.00
    蹙
    1.00
    Activations Density 0.002%

    No Known Activations