© 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. 13891
    Prev
    Next
    INDEX
    Explanations

    old sentenced

    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
     araña
    -1.70
     almohada
    -1.66
     Bagian
    -1.65
    ଃ
    -1.63
     muñeca
    -1.54
     engend
    -1.53
     orilla
    -1.52
    翃
    -1.49
     ducha
    -1.48
     réve
    -1.47
    POSITIVE LOGITS
    '
    1.98
     of
    1.60
    许久
    1.52
    🤯
    1.50
     and
    1.44
    ”
    1.35
     —
    1.35
    hhhhh
    1.34
    our
    1.32
     Chem
    1.30
    Activations Density 0.074%

    No Known Activations