© 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. 33523
    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
      
    -1.06
    </b>
    -1.04
     adentro
    -1.02
    m
    -1.00
     Even
    -0.98
    !
    -0.96
     are
    -0.94
     begins
    -0.94
    -0.93
    @
    -0.92
    POSITIVE LOGITS
    ឵
    1.18
    ᠌
    1.16
    鈀
    1.13
     案例
    1.13
    prendre
    1.12
    still
    1.12
    ⚌
    1.11
     preſent
    1.05
     Celebrating
    1.05
    nexo
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.