© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185860
    Prev
    Next
    INDEX
    Explanations

    words and phrases denoting actions

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

    specific noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -]+
    0.47
    )..
    0.44
     Louvre
    0.44
     DISABLE
    0.43
     лам
    0.43
     sprawl
    0.42
    یل
    0.42
    ..)
    0.42
     ôm
    0.42
     disadvantaged
    0.40
    POSITIVE LOGITS
    行動
    0.53
    活動
    0.52
    ✩
    0.51
    電話
    0.50
    west
    0.48
    公園
    0.48
     ۱۰
    0.47
     কর্মকান্ড
    0.47
    ユ
    0.47
    居住
    0.47
    Activations Density 0.000%

    No Known Activations