© 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. 98320
    Prev
    Next
    INDEX
    Explanations

    programming keywords and methods

    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
    があり
    -1.48
    などは
    -1.39
    で
    -1.34
    を
    -1.30
    などを
    -1.30
    をはじめ
    -1.28
    を含
    -1.25
    もあります
    -1.25
    さすがに
    -1.24
    のような
    -1.22
    POSITIVE LOGITS
     that
    1.58
     which
    1.35
    んですよ
    1.31
     any
    1.30
    擷
    1.30
     meticulous
    1.27
    胧
    1.27
     streamlined
    1.20
     meticulously
    1.20
    łoży
    1.20
    Activations Density 0.129%

    No Known Activations