© 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. 66482
    Prev
    Next
    INDEX
    Explanations

    Qatar, March, Mol

    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
    -1.66
     even
    -1.44
    ції
    -1.41
    ੀ
    -1.38
    ৫
    -1.36
    次的
    -1.35
     malu
    -1.34
    Хотя
    -1.34
     mahu
    -1.32
     of
    -1.30
    POSITIVE LOGITS
     
    1.77
     pâtes
    1.29
     dormitórios
    1.27
     cubiertos
    1.23
    却不
    1.20
     and
    1.19
     patrulla
    1.18
    却又
    1.17
     For
    1.17
    ↵↵
    1.17
    Activations Density 0.004%

    No Known Activations