© 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. 66278
    Prev
    Next
    INDEX
    Explanations

    descriptive word followed by related noun

    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
     or
    -1.60
     to
    -1.48
     verlangt
    -1.20
     such
    -1.20
     more
    -1.17
     біль
    -1.16
    いわゆる
    -1.14
     niega
    -1.13
     manifestó
    -1.13
     найбіль
    -1.08
    POSITIVE LOGITS
    attendre
    1.41
    ệp
    1.40
     概要
    1.38
     própri
    1.38
    UNTE
    1.36
    hány
    1.36
    ích
    1.34
    
    1.34
    ской
    1.33
    ("}");
    1.33
    Activations Density 0.005%

    No Known Activations