© 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. 551
    Prev
    Next
    INDEX
    Explanations

    managed resources

    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
     extremely
    -1.14
     diverses
    -1.13
     dando
    -1.12
     связанные
    -1.12
     sturdy
    -1.12
     innych
    -1.10
    fotografia
    -1.10
     either
    -1.09
     discreet
    -1.09
     alcune
    -1.07
    POSITIVE LOGITS
    Another
    1.23
    Every
    1.22
    (^_^;)
    1.18
    Getting
    1.18
    Having
    1.17
     Those
    1.16
    Putting
    1.15
     phenomenal
    1.14
    Almost
    1.14
    Because
    1.14
    Activations Density 0.000%

    No Known Activations