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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11468
    Prev
    Next
    INDEX
    Explanations

    scientific methods and techniques

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

    scientific terminology related to molecular biology methods and techniques.

    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
     правительства
    -1.60
     they
    -1.48
     パソコン
    -1.38
     aparcamiento
    -1.37
     promociones
    -1.34
    營業時間
    -1.30
     llegamos
    -1.30
     السياس
    -1.27
    ėmis
    -1.27
     descuentos
    -1.26
    POSITIVE LOGITS
     سينما
    1.42
     مباراة
    1.40
     препара
    1.39
    登上
    1.30
    }}>
    1.27
     to
    1.27
    hoka
    1.20
    rester
    1.16
    oprop
    1.15
    ולוג
    1.15
    Activations Density 0.552%

    No Known Activations