© 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. 75531
    Prev
    Next
    INDEX
    Explanations

    biological targets

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

    therapeutic targets for disease treatment in medical and scientific texts.

    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
     there
    -1.60
     помощью
    -1.52
    .
    -1.40
    ers
    -1.39
     irgend
    -1.38
    其余
    -1.36
     facilidad
    -1.34
     capucha
    -1.30
     You
    -1.30
    </h3>
    -1.30
    POSITIVE LOGITS
     to
    2.45
    formatics
    1.61
     ステン
    1.58
     the
    1.55
    бира
    1.46
    蟜
    1.46
    ijnlijk
    1.45
    ſam
    1.42
    bundet
    1.40
     BRARY
    1.40
    Activations Density 0.068%

    No Known Activations