© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13572
    Prev
    Next
    INDEX
    Explanations

    set the stage

    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
    intendo
    -1.44
    Anyways
    -1.38
     then
    -1.37
    siamo
    -1.36
    ballon
    -1.35
    <0x00>
    -1.34
    Etc
    -1.34
    damen
    -1.32
     nœ
    -1.30
     namelijk
    -1.30
    POSITIVE LOGITS
    лтемелер
    1.77
    neurial
    1.63
     iNdEx
    1.51
    ،
    1.49
    。
    1.47
    ]-->
    1.46
    罒
    1.46
    il
    1.46
     fijo
    1.46
     و
    1.44
    Activations Density 0.084%

    No Known Activations