© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54507
    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
    djang
    -1.24
    mtb
    -1.21
     juſ
    -1.17
    ụy
    -1.08
     Karakter
    -1.07
    kese
    -1.06
    yyb
    -1.05
     Perang
    -1.05
    ansible
    -1.04
    teddy
    -1.03
    POSITIVE LOGITS
     =
    1.06
     erforder
    1.05
    sch
    1.05
    ier
    1.04
    target
    1.02
    ner
    1.02
    ann
    1.02
    ai
    1.01
    da
    1.01
    ies
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.