© 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. 36724
    Prev
    Next
    INDEX
    Explanations

    track listing song

    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
     should
    -1.16
    While
    -1.13
     also
    -1.11
    Since
    -1.10
     for
    -1.08
     because
    -1.07
     Although
    -1.04
    Although
    -1.04
     While
    -1.04
     both
    -1.04
    POSITIVE LOGITS
     første
    1.29
     beginning
    1.28
     första
    1.23
     introductory
    1.16
     opening
    1.14
     arrival
    1.09
     první
    1.07
     temi
    1.05
    );?>
    1.04
     sonidos
    1.03
    Activations Density 0.055%

    No Known Activations