© 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. 71333
    Prev
    Next
    INDEX
    Explanations

    not attempted

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     NÃO
    -1.37
     TAMBÉM
    -1.36
     ܙ
    -1.32
     dát
    -1.30
    Также
    -1.25
     Eſ
    -1.21
     niedersachsen
    -1.20
    킁
    -1.19
     certains
    -1.18
     Inſ
    -1.18
    POSITIVE LOGITS
     there
    2.06
     available
    1.80
     included
    1.68
     any
    1.30
    There
    1.26
    there
    1.26
     until
    1.22
     essential
    1.22
     esiste
    1.18
     this
    1.14
    Activations Density 0.042%

    No Known Activations