© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77800
    Prev
    Next
    INDEX
    Explanations

    natural history and scientific institutions

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

    names of museums or references to museum collections and archives.

    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
     below
    -0.86
    视角
    -0.78
     Bardzo
    -0.75
    mCamera
    -0.74
     Gdy
    -0.73
     Dzięki
    -0.73
     Jeśli
    -0.72
    嫦
    -0.72
    のご
    -0.71
     diaper
    -0.71
    POSITIVE LOGITS
    Natural
    1.77
     Natural
    1.56
     NATURAL
    1.52
    NATURAL
    1.52
     natural
    1.48
    natural
    1.43
    自然
    1.34
     自然
    1.13
     museum
    1.10
    Specimen
    1.07
    Activations Density 0.023%

    No Known Activations