© 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. 73967
    Prev
    Next
    INDEX
    Explanations

    ensuring that

    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
     to
    -1.53
     but
    -1.50
     It
    -1.39
     by
    -1.33
     after
    -1.30
    *}[
    -1.27
     since
    -1.24
     Тогда
    -1.23
     comenzaron
    -1.22
    ophil
    -1.21
    POSITIVE LOGITS
     each
    1.42
     your
    1.38
    不会
    1.28
    注意事
    1.27
     alip
    1.22
     everything
    1.21
     wako
    1.21
     everyone
    1.20
     graden
    1.17
     our
    1.16
    Activations Density 0.019%

    No Known Activations