© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75165
    Prev
    Next
    INDEX
    Explanations

    for availability

    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
    ዣ
    -1.53
     anlay
    -1.44
    絎
    -1.43
     髪型
    -1.41
    Ꮫ
    -1.38
     persua
    -1.38
     sensib
    -1.37
    
    -1.36
    Garten
    -1.35
     mostrare
    -1.35
    POSITIVE LOGITS
     or
    2.13
     and
    1.68
     as
    1.63
     from
    1.50
     for
    1.41
     but
    1.41
     since
    1.40
     which
    1.33
     at
    1.31
    思議
    1.25
    Activations Density 0.056%

    No Known Activations