© 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. 22-GEMMASCOPE-RES-131K
    7. 104498
    Prev
    Next
    INDEX
    Explanations

    bibliography followed by colon and file

    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
     for
    -1.28
     as
    -1.26
     if
    -1.23
     when
    -1.17
     their
    -1.15
    ↵↵
    -1.14
     or
    -1.10
     on
    -1.04
     While
    -1.03
     would
    -1.02
    POSITIVE LOGITS
     crappy
    1.28
     санкт
    1.20
     nowy
    1.20
    ཿ
    1.18
     koń
    1.14
     terlaris
    1.14
    quarie
    1.13
     jednej
    1.13
    ۀ
    1.13
     requiere
    1.09
    Activations Density 0.003%

    No Known Activations