© 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. 25705
    Prev
    Next
    INDEX
    Explanations

    film titles and 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
     their
    -1.80
     there
    -1.42
     if
    -1.32
     this
    -1.26
     at
    -1.23
     now
    -1.22
     with
    -1.21
     usually
    -1.17
    。『
    -1.13
     provide
    -1.13
    POSITIVE LOGITS
     komfor
    1.44
     verhind
    1.36
     erhi
    1.33
    卺
    1.31
     peintures
    1.29
     zoude
    1.29
     pâtes
    1.27
     deklar
    1.25
    worden
    1.24
    passen
    1.23
    Activations Density 0.056%

    No Known Activations