© 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. 73331
    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
     very
    -1.14
     actually
    -1.12
     during
    -0.96
    During
    -0.93
     could
    -0.91
     their
    -0.91
     both
    -0.90
    updateTime
    -0.90
     obtain
    -0.90
     early
    -0.88
    POSITIVE LOGITS
    liament
    1.09
    ख्या
    1.08
     stedet
    1.05
     quadrinhos
    1.03
     HRC
    1.01
     následu
    1.00
     plaintext
    0.99
     Camaro
    0.97
    lexus
    0.96
    椋
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.