© 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. 68626
    Prev
    Next
    INDEX
    Explanations

    ac, alt, particulate, final, c, os, 3

    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
    事も
    -1.45
    様な
    -1.45
    為に
    -1.41
    事が
    -1.39
    事は
    -1.34
    ようです
    -1.34
    ところです
    -1.30
    ごとの
    -1.30
    わけです
    -1.29
    ようで
    -1.27
    POSITIVE LOGITS
     just
    1.55
     can
    1.52
     (
    1.50
     that
    1.44
     in
    1.44
     with
    1.41
     first
    1.34
     but
    1.31
     could
    1.28
     before
    1.26
    Activations Density 0.241%

    No Known Activations