© 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. 72644
    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
     that
    -1.58
     kompati
    -1.58
     kabát
    -1.50
     salonu
    -1.45
     Paramètres
    -1.43
     hjer
    -1.38
     mikina
    -1.37
     navn
    -1.36
     powodu
    -1.36
     stratég
    -1.35
    POSITIVE LOGITS
    on
    1.27
     лишь
    1.23
    ↵↵
    1.17
     =
    1.16
     l
    1.12
     But
    1.10
     also
    1.09
     B
    1.06
     They
    1.06
     A
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.