© 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. 10-GEMMASCOPE-RES-131K
    7. 8169
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ⇴
    -1.40
    Yet
    -1.37
    Our
    -1.35
    Still
    -1.30
    Even
    -1.20
    Here
    -1.20
    ced
    -1.20
    times
    -1.18
    ger
    -1.16
     Cowboys
    -1.16
    POSITIVE LOGITS
     they
    1.58
     that
    1.43
     such
    1.34
     this
    1.33
     there
    1.15
    䊐
    1.14
     like
    1.12
     săptăm
    1.12
     bestaande
    1.11
     femei
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.