© 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. 10-GEMMASCOPE-RES-131K
    7. 7633
    Prev
    Next
    INDEX
    Explanations

    names and asthma

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

    names of people or places, particularly from South Asia or Australia.

    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
    !’
    -2.80
    峩
    -2.75
    u
    -2.61
    壆
    -2.34
    ?’
    -2.34
    勿論
    -2.28
    哢
    -2.27
    葶
    -2.25
     prodej
    -2.22
     řed
    -2.19
    POSITIVE LOGITS
    The
    3.44
    .,
    3.05
    й
    3.02
    ',
    2.84
     \
    2.84
    a
    2.84
    $,
    2.77
    ),
    2.77
    ,.
    2.77
    –
    2.69
    Activations Density 0.010%

    No Known Activations