© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34665
    Prev
    Next
    INDEX
    Explanations

    vintage items and collections

    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
     on
    -2.02
     at
    -1.49
     with
    -1.30
     four
    -1.27
     first
    -1.25
     without
    -1.15
     only
    -1.13
     already
    -1.13
     changed
    -1.12
     immediately
    -1.09
    POSITIVE LOGITS
     alcune
    1.36
     alcuni
    1.35
    seems
    1.34
     anciennes
    1.25
     épu
    1.23
     magnifiques
    1.21
    Seems
    1.20
    킁
    1.20
    mostly
    1.19
     decades
    1.18
    Activations Density 0.022%

    No Known Activations