© 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. 26228
    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
    signable
    -1.34
    datable
    -1.29
     \&
    -1.24
     alegre
    -1.20
    usions
    -1.17
    🟢
    -1.17
    \#:
    -1.16
    nees
    -1.16
    🧐
    -1.16
    lighed
    -1.16
    POSITIVE LOGITS
    Selanjutnya
    1.35
     esquecer
    1.35
     sofrer
    1.35
     copertina
    1.32
     aceitar
    1.30
     necesitar
    1.29
     mudou
    1.29
     tendenza
    1.28
     pubblicità
    1.27
     taglio
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.