© 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. 34-GEMMASCOPE-RES-131K
    7. 38186
    Prev
    Next
    INDEX
    Explanations

    wife Shanti

    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_34/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
    色々な
    -1.45
     hauptsächlich
    -1.44
     used
    -1.28
     because
    -1.27
    いろいろな
    -1.25
     różne
    -1.24
     using
    -1.23
     different
    -1.21
     famous
    -1.20
     INFORMACIÓN
    -1.19
    POSITIVE LOGITS
    Alike
    1.42
     ought
    1.28
    beit
    1.19
     alike
    1.17
    pshot
    1.15
    Folks
    1.15
    unno
    1.15
    ১
    1.15
     whatsoever
    1.13
    dirond
    1.12
    Activations Density 0.159%

    No Known Activations