© 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. 73354
    Prev
    Next
    INDEX
    Explanations

    Nothing followed by verbs

    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
    涐
    -3.69
    ㍑
    -3.03
    鱨
    -2.81
     baumwolle
    -2.77
    槼
    -2.73
     広場
    -2.69
    瞜
    -2.58
     diza
    -2.55
     pietre
    -2.53
     turisti
    -2.52
    POSITIVE LOGITS
    .
    4.09
     For
    2.81
     If
    2.52
     else
    2.47
     It
    2.44
     n
    2.31
     A
    2.30
     Our
    2.25
     )
    2.25
     e
    2.22
    Activations Density 0.018%

    No Known Activations