© 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. 35390
    Prev
    Next
    INDEX
    Explanations

    endings like son, pherd, ffer, cker

    np_acts-logits-general · gemini-2.5-flash-lite

    the bylines and author credit lines (names, email or social‐media handles) in articles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    !
    -1.73
    .
    -1.27
    ,
    -1.23
     our
    -1.21
     
    -1.20
     people
    -1.19
    /
    -1.18
     Това
    -1.13
     H
    -1.09
     FOR
    -1.09
    POSITIVE LOGITS
     faciliter
    1.64
     geene
    1.41
    Ár
    1.36
     katk
    1.34
     rimanere
    1.34
     пун
    1.33
     rapporter
    1.32
     utilizada
    1.32
    がありますが
    1.31
    Prezzo
    1.31
    Activations Density 0.007%

    No Known Activations