© 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. 73687
    Prev
    Next
    INDEX
    Explanations

    one such example

    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
    Other
    -1.41
    Berikut
    -1.33
     либо
    -1.30
     Even
    -1.28
    要么
    -1.23
    Even
    -1.20
    *,
    -1.16
    There
    -1.15
     you
    -1.13
     There
    -1.13
    POSITIVE LOGITS
     such
    1.36
    Backdrop
    1.34
     tijdens
    1.24
    1.21
     साधारण
    1.20
    komt
    1.20
    манда
    1.19
     Mathem
    1.16
    pagnole
    1.16
    camis
    1.15
    Activations Density 0.067%

    No Known Activations