© 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. 65952
    Prev
    Next
    INDEX
    Explanations

    places and institutions

    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
    NARR
    -1.30
     творо
    -1.23
     mentira
    -1.18
     сыром
    -1.16
     lantaran
    -1.15
     usai
    -1.14
     ویتامین
    -1.12
     fraude
    -1.11
     sedia
    -1.11
     sirup
    -1.09
    POSITIVE LOGITS
     selected
    1.41
     located
    1.30
     katika
    1.27
    וּ
    1.20
     their
    1.19
     Савез
    1.14
     fuß
    1.14
     различни
    1.10
     voren
    1.06
     Läng
    1.05
    Activations Density 0.075%

    No Known Activations