© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128107
    Prev
    Next
    INDEX
    Explanations

    populating data

    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
    秾
    -1.44
    
    -1.39
    ۶
    -1.38
    
    -1.28
     hinten
    -1.28
     decimos
    -1.27
     keines
    -1.27
    ۳
    -1.27
     totalement
    -1.25
    Twice
    -1.23
    POSITIVE LOGITS
     and
    1.76
     for
    1.57
     which
    1.56
     According
    1.42
     according
    1.38
     Obviously
    1.34
     based
    1.32
     the
    1.31
     Typically
    1.28
    桎
    1.23
    Activations Density 0.070%

    No Known Activations