© 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. 14809
    Prev
    Next
    INDEX
    Explanations

    people, places, organizations, and events

    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
     camisetas
    -1.41
     histó
    -1.40
    från
    -1.39
    Rozmiar
    -1.38
    𖦹
    -1.31
    ранее
    -1.30
     músculo
    -1.28
     botas
    -1.28
     menurun
    -1.27
     dátum
    -1.24
    POSITIVE LOGITS
     …
    1.48
     ...
    1.41
    ۀ
    1.37
    p
    1.34
    op
    1.27
    l
    1.25
    u
    1.24
    e
    1.23
    を
    1.23
    P
    1.19
    Activations Density 0.026%

    No Known Activations