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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7362
    Prev
    Next
    INDEX
    Explanations

    diverse environments and habitats

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

    descriptions of natural habitats and ecosystems, particularly focusing on forest, savanna, and ecological zones.

    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
     the
    -1.81
     nung
    -1.61
    も含
    -1.61
    ísimas
    -1.52
    ݯ
    -1.52
    ︲
    -1.49
    に来
    -1.48
     about
    -1.48
     a
    -1.45
    lya
    -1.45
    POSITIVE LOGITS
     of
    1.77
    There
    1.66
    These
    1.48
    Unlike
    1.47
    ↵↵
    1.46
     Beide
    1.45
    While
    1.44
     where
    1.43
     этого
    1.42
     While
    1.41
    Activations Density 0.088%

    No Known Activations