© 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. 22-GEMMASCOPE-RES-131K
    7. 129807
    Prev
    Next
    INDEX
    Explanations

    commas followed by conjunctions

    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
     onsdag
    -1.27
     TÉ
    -1.27
     inalámbrico
    -1.26
     pensées
    -1.24
    РТ
    -1.18
    Ѕ
    -1.18
     réglable
    -1.17
    xvii
    -1.17
     japonés
    -1.16
    като
    -1.16
    POSITIVE LOGITS
     and
    2.41
     berbagai
    1.39
     will
    1.23
     realizzazione
    1.20
     or
    1.19
     at
    1.18
     seluruh
    1.13
     bahkan
    1.09
     as
    1.08
     pelbagai
    1.06
    Activations Density 0.004%

    No Known Activations