© 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. 73079
    Prev
    Next
    INDEX
    Explanations

    with options or callback

    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
     in
    -2.03
     on
    -1.77
     by
    -1.74
     with
    -1.64
     are
    -1.46
     and
    -1.46
     new
    -1.45
    🐾
    -1.36
     an
    -1.34
     all
    -1.33
    POSITIVE LOGITS
     vorgesehen
    1.61
     offensichtlich
    1.52
     angesehen
    1.46
     freilich
    1.45
     angeschlossen
    1.43
     festgestellt
    1.41
     berechtigt
    1.40
     geliefert
    1.38
     angefü
    1.38
     ulei
    1.36
    Activations Density 0.015%

    No Known Activations