© 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. 22-GEMMASCOPE-RES-131K
    4. 65661
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     decisively
    -1.61
     disregarding
    -1.58
     fatally
    -1.58
     furiously
    -1.56
     brutally
    -1.52
     smartly
    -1.48
     solidly
    -1.48
     focussing
    -1.48
     convincingly
    -1.48
     focussed
    -1.48
    POSITIVE LOGITS
    );
    1.29
     These
    1.24
    ).
    1.24
     To
    1.23
    ),
    1.22
     сих
    1.16
    has
    1.13
    by
    1.12
     Such
    1.10
     They
    1.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.