© 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. 39370
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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
     parfü
    -2.02
     parfüm
    -1.90
     didik
    -1.69
     öde
    -1.68
     kabát
    -1.68
    Öl
    -1.63
     mempel
    -1.62
    Während
    -1.59
    Keine
    -1.58
     mengenal
    -1.52
    POSITIVE LOGITS
     
    1.42
     last
    1.41
    $
    1.40
    --
    1.37
    a
    1.33
    ,
    1.33
    —
    1.31
    <em>
    1.30
    ”
    1.30
     N
    1.29
    Activations Density 0.003%

    No Known Activations