© 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. 1022
    Prev
    Next
    INDEX
    Explanations

    Poisson regression and distributions

    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
    .”
    -2.75
    acterísticas
    -2.66
    actéristi
    -2.63
     selben
    -2.55
    ଢ
    -2.48
    تیجه
    -2.41
    ……」
    -2.36
    撄
    -2.28
    ou
    -2.25
    ﮏ
    -2.25
    POSITIVE LOGITS
    灩
    2.69
     mélange
    2.33
     $
    2.27
    the
    2.09
    あえず
    2.02
    
    2.02
     そば
    1.99
     encontram
    1.98
    槼
    1.98
    <i>
    1.97
    Activations Density 0.002%

    No Known Activations