© 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. 22-GEMMASCOPE-RES-131K
    7. 129450
    Prev
    Next
    INDEX
    Explanations

    our health issues

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

    content that provides professional healthcare or medical service information.

    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
     цвят
    -1.21
    了不少
    -1.15
    ϰ
    -1.09
    וּ
    -1.03
    想过
    -1.03
     Gleichzeitig
    -1.03
     ihres
    -1.02
     gezicht
    -1.00
     Ähnliche
    -0.99
    Nucl
    -0.97
    POSITIVE LOGITS
     our
    2.28
     your
    2.06
     you
    1.73
    OUR
    1.62
    我们
    1.59
    your
    1.49
     OUR
    1.48
     we
    1.45
     Our
    1.43
     votre
    1.43
    Activations Density 0.019%

    No Known Activations