© 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. 117396
    Prev
    Next
    INDEX
    Explanations

    thematic units

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

    deliver speeches

    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
    ंकि
    0.44
    फ़ी
    0.44
    ो
    0.44
    妤
    0.43
    ме
    0.43
    archy
    0.43
    hension
    0.43
    基础设施
    0.42
     बंगला
    0.42
    ປັນ
    0.42
    POSITIVE LOGITS
    sburg
    0.44
    s
    0.44
    ‾
    0.44
    𝐪
    0.44
    =");
    0.44
     versus
    0.43
     import
    0.43
     Pon
    0.43
     recruits
    0.42
     durability
    0.42
    Activations Density 0.001%

    No Known Activations