© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110440
    Prev
    Next
    INDEX
    Explanations

    extraction and chemical analysis

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

    chemical extraction methods and reagents used in laboratory procedures.

    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_34/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
     programs
    -0.84
    räume
    -0.79
     Sug
    -0.76
    ギュラー
    -0.76
    Since
    -0.76
    бака
    -0.76
     floors
    -0.75
    omon
    -0.75
    Quite
    -0.74
     scho
    -0.74
    POSITIVE LOGITS
    Notify
    0.83
    淪
    0.82
    jących
    0.82
    saturated
    0.77
     Literatura
    0.77
     Lillie
    0.77
    owymi
    0.76
    冽
    0.72
     Solution
    0.72
     Izzy
    0.71
    Activations Density 0.024%

    No Known Activations