© 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. 38964
    Prev
    Next
    INDEX
    Explanations

    Myers and Hymenoptera

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

    the surname "Myers" or variations of it.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the surname “Myers” in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -3.94
    ,"
    -3.33
    "
    -3.23
    —
    -3.09
    )-
    -3.06
    1
    -3.02
    (
    -3.00
    I
    -2.83
     If
    -2.77
    0
    -2.73
    POSITIVE LOGITS
    鸶
    2.94
    龊
    2.83
    ﯼ
    2.81
    蘗
    2.81
    鮠
    2.77
    錞
    2.75
    𓍊
    2.72
    泺
    2.72
    鼍
    2.67
    栊
    2.59
    Activations Density 0.002%

    No Known Activations