© 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. 130928
    Prev
    Next
    INDEX
    Explanations

    sentence starters

    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
     what
    -1.34
     and
    -1.31
    ˮ
    -1.29
     or
    -1.25
    *
    -1.24
     on
    -1.23
    muito
    -1.20
    izzazioni
    -1.20
     with
    -1.19
    我們
    -1.18
    POSITIVE LOGITS
     they
    2.14
    もあって
    1.38
     다른
    1.35
     largely
    1.27
     said
    1.23
    despite
    1.23
    atrième
    1.20
    はなく
    1.20
    due
    1.20
     entire
    1.20
    Activations Density 0.007%

    No Known Activations