© 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. 100826
    Prev
    Next
    INDEX
    Explanations

    products and materials

    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_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
     тільки
    -1.23
     только
    -1.13
    落ち着いた
    -1.10
     знаем
    -1.08
    ől
    -1.06
     gelukkig
    -1.06
     čern
    -1.05
    に向かって
    -1.04
    Entrevista
    -1.03
    čného
    -1.02
    POSITIVE LOGITS
     things
    1.30
     copertina
    1.28
     by
    1.28
    Other
    1.19
     TAMBÉM
    1.15
    ologues
    1.14
    始める
    1.13
     my
    1.12
    Autres
    1.12
    Users
    1.10
    Activations Density 0.130%

    No Known Activations