© 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. 65967
    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
     Livre
    -1.19
     hunde
    -1.14
     its
    -1.13
     Souver
    -1.12
    ❗️
    -1.08
    :✨
    -1.08
    <()>
    -1.08
     Tuhan
    -1.05
    lampu
    -1.04
    "">
    -1.02
    POSITIVE LOGITS
     mehrerer
    1.20
     áng
    1.16
     asemenea
    1.13
     LOOKS
    1.09
     subgoal
    1.09
     takich
    1.09
     оцени
    1.08
     toutefois
    1.08
     vieler
    1.08
     CANNOT
    1.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.