© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22346
    Prev
    Next
    INDEX
    Explanations

    finding a solution or working

    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
     is
    -1.16
    桶
    -1.15
    яза
    -1.14
    *
    -1.13
     no
    -1.11
    seudo
    -1.06
     clair
    -1.05
    8
    -1.05
     Jams
    -1.05
     e
    -1.05
    POSITIVE LOGITS
     those
    1.73
     their
    1.51
     Ultimately
    1.33
     what
    1.31
    մ
    1.30
     from
    1.28
    ”:
    1.22
     them
    1.22
     lembar
    1.21
     five
    1.18
    Activations Density 0.034%

    No Known Activations