© 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. 7830
    Prev
    Next
    INDEX
    Explanations

    actually

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

    actually

    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
     asimismo
    0.36
     dược
    0.36
    상품
    0.34
    Outline
    0.34
     useParams
    0.34
    న్‌లో
    0.33
    𝚊
    0.33
    鿉
    0.33
    okkal
    0.32
     lợi
    0.32
    POSITIVE LOGITS
     actually
    0.92
     Actually
    0.91
    actually
    0.87
    其实
    0.86
     aslında
    0.82
    其實
    0.81
     sebenarnya
    0.80
    Actually
    0.80
     एक्चुअली
    0.78
    实际上
    0.77
    Activations Density 0.239%

    No Known Activations