© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130012
    Prev
    Next
    INDEX
    Explanations

    play-offs, strike, division, prize, Santa

    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_10/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
    无法
    -1.29
    istream
    -1.11
     Item
    -1.06
     pensent
    -1.05
    >=</
    -1.05
    etlen
    -1.05
     inoxidable
    -1.01
    ごめんなさい
    -0.98
     diversas
    -0.96
     Brasile
    -0.96
    POSITIVE LOGITS
     any
    1.35
     kilometr
    1.23
     hva
    1.20
     same
    1.19
     photographers
    1.13
     Copying
    1.13
    už
    1.12
    ſon
    1.12
     Spanien
    1.09
     its
    1.09
    Activations Density 0.225%

    No Known Activations