© 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. 22-GEMMASCOPE-RES-131K
    7. 26227
    Prev
    Next
    INDEX
    Explanations

    research or study descriptions

    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
     there
    -1.90
     hundreds
    -1.79
     these
    -1.69
     with
    -1.66
     chré
    -1.65
     many
    -1.59
     when
    -1.57
     would
    -1.55
     even
    -1.54
     how
    -1.52
    POSITIVE LOGITS
     IActionResult
    1.56
     gouttes
    1.44
    を購入
    1.43
     مباراة
    1.40
     également
    1.40
    Bitcoin
    1.38
     бампер
    1.37
    ﻷ
    1.35
     fraî
    1.34
    UnusedPrivate
    1.34
    Activations Density 0.307%

    No Known Activations