© 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. 10-GEMMASCOPE-RES-131K
    7. 123924
    Prev
    Next
    INDEX
    Explanations

    tasks and chores

    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
    ஂ
    -2.98
    ਞ
    -2.66
    谖
    -2.48
    d
    -2.39
     finds
    -2.39
    自身的
    -2.31
    
    -2.30
    üğü
    -2.27
    韡
    -2.20
    which
    -2.19
    POSITIVE LOGITS
    1
    2.80
    買った
    2.23
     pike
    2.14
    3
    2.13
     kämpfen
    2.09
     Abstand
    2.09
    餮
    2.06
     renown
    2.05
     Namun
    2.02
     Selain
    2.02
    Activations Density 0.001%

    No Known Activations