© 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. 66384
    Prev
    Next
    INDEX
    Explanations

    titles and phrases

    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
    -2.52
     this
    -2.33
     only
    -2.28
     even
    -2.27
     an
    -2.25
     more
    -2.23
     one
    -2.16
     with
    -2.16
     also
    -2.16
     at
    -2.14
    POSITIVE LOGITS
     Dinas
    2.00
     alcune
    1.99
    brtc
    1.93
     PERFECT
    1.93
     AMAZING
    1.91
     alcuni
    1.90
     molti
    1.85
    ܆
    1.85
    Kleur
    1.85
     peuvent
    1.84
    Activations Density 0.145%

    No Known Activations