© 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. 103593
    Prev
    Next
    INDEX
    Explanations

    always positive sentiment

    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
     what
    -1.50
     lento
    -1.42
     utensi
    -1.38
     lampa
    -1.35
    чня
    -1.33
    plona
    -1.30
     Nederlands
    -1.30
     Jeux
    -1.29
     Dansk
    -1.27
     hvad
    -1.27
    POSITIVE LOGITS
     of
    1.69
     mehreren
    1.53
     красивые
    1.46
     dowol
    1.44
    as
    1.43
     několik
    1.36
     ContentValues
    1.34
    best
    1.34
     choice
    1.30
     pairs
    1.29
    Activations Density 0.023%

    No Known Activations