© 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. 36578
    Prev
    Next
    INDEX
    Explanations

    comment markers and code separators

    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
     with
    -2.42
     if
    -2.31
     for
    -2.19
     before
    -2.17
     more
    -2.17
     on
    -2.08
     when
    -2.08
     seven
    -2.06
     every
    -2.05
     as
    -2.02
    POSITIVE LOGITS
     REALLY
    2.39
     insanely
    2.20
     wondrous
    2.13
     unbelievably
    2.11
     DURING
    2.11
     ridiculously
    2.11
     AMAZING
    2.11
     amazingly
    2.08
     VERY
    2.06
     alluring
    2.05
    Activations Density 0.005%

    No Known Activations