© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73788
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    _),
    -1.59
    beleid
    -1.58
     to
    -1.52
     on
    -1.45
    )}</
    -1.42
    '])->
    -1.39
    )]
    
    -1.38
    ')(
    -1.38
     with
    -1.37
    ".
    
    -1.35
    POSITIVE LOGITS
    頂きました
    1.66
     we
    1.60
     they
    1.49
     Auswirkungen
    1.36
    Where
    1.34
    観て
    1.34
    Why
    1.32
    を読む
    1.30
    Specifically
    1.30
    実際に
    1.29
    Activations Density 0.134%

    No Known Activations