© 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. 128725
    Prev
    Next
    INDEX
    Explanations

    liquid, pin, pivotal

    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
     sprüche
    -1.56
     runde
    -1.54
    かというと
    -1.51
     farbe
    -1.45
     ventre
    -1.45
    İN
    -1.45
     ché
    -1.45
     victoires
    -1.42
     seksual
    -1.40
     bâtiment
    -1.38
    POSITIVE LOGITS
    _
    1.74
     where
    1.58
     is
    1.47
     without
    1.30
    了一遍
    1.27
    って何
    1.23
    /
    1.23
    了一会儿
    1.20
    日起
    1.18
     opět
    1.17
    Activations Density 0.239%

    No Known Activations