© 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. 22-GEMMASCOPE-RES-131K
    7. 27343
    Prev
    Next
    INDEX
    Explanations

    followed by

    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_22/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
     which
    -1.84
     while
    -1.45
     through
    -1.38
     if
    -1.34
     because
    -1.30
     from
    -1.30
     only
    -1.29
     with
    -1.27
     facilitates
    -1.21
     since
    -1.18
    POSITIVE LOGITS
     biet
    1.09
     luscious
    1.04
     diversos
    1.03
     coloca
    0.99
     hacen
    0.99
     య
    0.99
     gigantic
    0.98
     fazendo
    0.98
     horrid
    0.98
     vuelve
    0.97
    Activations Density 0.052%

    No Known Activations