© 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. 65726
    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
     all
    -1.53
     have
    -1.51
     their
    -1.48
     even
    -1.41
     this
    -1.37
    之后
    -1.26
     found
    -1.16
     helped
    -1.15
     additional
    -1.12
    URDAY
    -1.12
    POSITIVE LOGITS
    excellents
    1.33
    螓
    1.27
     aceptas
    1.21
    STRUCTION
    1.20
     caricature
    1.20
    Yeni
    1.19
    wesenheit
    1.18
     alguns
    1.16
    kennung
    1.16
    CTIONS
    1.13
    Activations Density 0.000%

    No Known Activations