© 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. 84175
    Prev
    Next
    INDEX
    Explanations

    formal execution of tasks

    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
    ,
    -3.02
     and
    -1.98
     it
    -1.86
    :
    -1.79
     any
    -1.78
    ;
    -1.70
     when
    -1.70
     one
    -1.66
    2
    -1.66
     while
    -1.65
    POSITIVE LOGITS
    鹩
    2.08
     ۳
    1.91
     ۱۰
    1.84
    ᕮ
    1.77
     intptr
    1.73
    粜
    1.73
    curities
    1.73
     '-':
    1.71
     ۴
    1.71
    ENTS
    1.70
    Activations Density 28.638%

    No Known Activations