© 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. 10-GEMMASCOPE-RES-131K
    7. 70192
    Prev
    Next
    INDEX
    Explanations

    general and admiral titles

    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_10/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
     permitiendo
    -1.70
     encontrados
    -1.55
    the
    -1.47
    which
    -1.43
                    
    -1.43
    erapeutics
    -1.38
     cayó
    -1.34
    与此
    -1.33
                             
    -1.31
     which
    -1.31
    POSITIVE LOGITS
     of
    2.75
    鉿
    1.35
     解析
    1.31
    Viitteet
    1.30
     副本
    1.30
    雰
    1.30
     into
    1.29
     cuarenta
    1.28
    ⅘
    1.27
    .
    1.26
    Activations Density 0.018%

    No Known Activations