© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6
    Prev
    Next
    INDEX
    Explanations

    Flash player and content

    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
     we
    -1.36
    u
    -1.23
    c
    -1.19
    "...
    -1.18
    d
    -1.16
     hebben
    -1.16
     he
    -1.13
     et
    -1.13
     you
    -1.09
    </sup>
    -1.09
    POSITIVE LOGITS
     brak
    1.48
    Ꭳ
    1.45
    ewear
    1.45
    dzić
    1.38
    crete
    1.34
    ージョン
    1.34
    underset
    1.30
    ндарт
    1.28
    鸶
    1.27
     jantung
    1.27
    Activations Density 0.110%

    No Known Activations