© 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. 22-GEMMASCOPE-RES-131K
    7. 26668
    Prev
    Next
    INDEX
    Explanations

    problem solved

    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
     jednej
    -1.18
     motoru
    -1.16
    ᕦ
    -1.11
     čase
    -1.10
     cóc
    -1.10
    fromDate
    -1.10
    uline
    -1.10
     baterie
    -1.09
     histó
    -1.09
     vín
    -1.09
    POSITIVE LOGITS
     now
    1.27
     it
    1.19
     they
    1.16
    !!
    1.13
     just
    1.11
    !
    1.10
     there
    1.09
     even
    1.05
    !!!
    1.05
     although
    1.05
    Activations Density 0.033%

    No Known Activations