© 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. 26779
    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
    TOBER
    -1.18
    MANUEL
    -1.10
    LEBR
    -1.09
    osas
    -1.02
    THERS
    -1.00
    fangs
    -0.96
     whofe
    -0.96
    yecek
    -0.96
     sembla
    -0.94
    БЕ
    -0.94
    POSITIVE LOGITS
     required
    1.04
     Venedig
    1.04
    Before
    0.96
     sogenannte
    0.96
     있다
    0.96
    Descriere
    0.95
    Although
    0.94
    With
    0.94
     somewhere
    0.94
     dred
    0.93
    Activations Density 0.000%

    No Known Activations