© 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. 72592
    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
    𝕋
    -1.03
    ·
    -1.02
     azule
    -1.02
     obſ
    -0.98
     azulejos
    -0.97
    --"
    -0.94
     escrit
    -0.94
     lança
    -0.93
    SBATCH
    -0.92
    ambilan
    -0.92
    POSITIVE LOGITS
     at
    1.06
     natomiast
    1.01
    市立
    1.01
     the
    0.99
    ぉ
    0.94
    at
    0.92
     gminy
    0.91
     mandatario
    0.89
    ª
    0.88
     et
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.