© 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. 33866
    Prev
    Next
    INDEX
    Explanations

    exception type or other

    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
     célè
    -1.35
     discuter
    -1.31
     pérd
    -1.30
     bénéficiaire
    -1.28
    dames
    -1.27
     花纹
    -1.27
     drapeau
    -1.24
     persiste
    -1.24
     réserver
    -1.24
     estadounid
    -1.23
    POSITIVE LOGITS
     other
    1.87
     Other
    1.53
     or
    1.42
    other
    1.36
    其它
    1.34
    อื่น
    1.32
     अन्य
    1.22
    Other
    1.19
    其他
    1.18
     S
    1.16
    Activations Density 0.001%

    No Known Activations