© 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. 22-GEMMASCOPE-RES-131K
    7. 15672
    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
     their
    -1.19
    mux
    -1.02
     it
    -0.99
    Ĵ
    -0.99
    ndig
    -0.97
    ʁ
    -0.94
    roides
    -0.94
    sillon
    -0.94
    цтва
    -0.94
    ܜ
    -0.93
    POSITIVE LOGITS
    KNOW
    1.02
     into
    0.90
    ctico
    0.89
    recently
    0.88
     peeking
    0.87
    telen
    0.86
    Minimize
    0.84
     bailarina
    0.84
    relate
    0.84
    MCA
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.