© 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. 98293
    Prev
    Next
    INDEX
    Explanations

    role followed by person's name

    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
     TAMBÉM
    -1.60
     zahlreichen
    -1.41
     mehreren
    -1.36
    事です
    -1.30
    にします
    -1.25
     "'";
    -1.20
    みを
    -1.19
    AllAfrica
    -1.16
    Accede
    -1.13
    Alguns
    -1.13
    POSITIVE LOGITS
     in
    1.21
    ྜ
    1.20
    erkek
    1.17
    我已经
    1.14
    ़
    1.13
    يمي
    1.10
    fürst
    1.09
    ных
    1.05
     Eventos
    1.05
     Príncipe
    1.05
    Activations Density 0.108%

    No Known Activations