© 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. 79791
    Prev
    Next
    INDEX
    Explanations

    program, page, or disorder names

    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
    -1.39
    :
    -1.26
     Each
    -1.05
     by
    -1.05
    僱
    -1.04
    子さん
    -1.02
     which
    -0.98
     such
    -0.98
     These
    -0.97
     intended
    -0.97
    POSITIVE LOGITS
     faciliter
    1.54
     acides
    1.36
    Αν
    1.29
     >=",
    1.29
    ,</
    1.26
    erobic
    1.23
    最近は
    1.23
     miRNAs
    1.23
    筴
    1.22
     gouttes
    1.20
    Activations Density 0.001%

    No Known Activations