© 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. 10-GEMMASCOPE-RES-131K
    7. 19002
    Prev
    Next
    INDEX
    Explanations

    gratitude professions medical conditions

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

    the beginning of a new entry or paragraph in a list or document, particularly in medical case reports or testimonials.

    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_10/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
    фикация
    -1.38
    axaca
    -1.34
     jendela
    -1.30
     verkaufen
    -1.27
    -1.26
     then
    -1.24
    vidades
    -1.23
     entretenimiento
    -1.20
    ální
    -1.17
     this
    -1.13
    POSITIVE LOGITS
    her
    1.14
    unico
    1.10
     even
    1.10
    нні
    1.09
     resultMap
    1.08
    y
    1.07
     together
    1.05
     herself
    1.05
    };*/
    1.05
     be
    1.02
    Activations Density 0.320%

    No Known Activations