© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28036
    Prev
    Next
    INDEX
    Explanations

    study counts and patient demographics

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

    numbers indicating the sample size in research studies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     might
    -1.36
     could
    -1.20
     perhaps
    -1.17
     communauté
    -1.13
     responsabilité
    -1.13
    letoe
    -1.11
     to
    -1.10
    了什么
    -1.09
    了几
    -1.09
     instead
    -1.09
    POSITIVE LOGITS
     of
    1.55
     sudad
    1.27
     especias
    1.23
     bañera
    1.22
     who
    1.17
     ваше
    1.16
     ſmall
    1.11
     colgantes
    1.08
     gastronomía
    1.08
     ваши
    1.07
    Activations Density 0.269%

    No Known Activations