© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 727
    Prev
    Next
    INDEX
    Explanations

    especially especially

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

    especially or particularly

    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_53_width_65k_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
    ，
    0.39
     เพื่อ
    0.36
    (),
    0.34
     затем
    0.33
     然後
    0.33
     потім
    0.31
    ،
    0.31
    )]$
    0.31
     Rồi
    0.30
    ര്‍ന്ന്
    0.30
    POSITIVE LOGITS
     especially
    1.95
    especially
    1.84
     особенно
    1.81
     particularly
    1.72
     Especially
    1.67
     especialmente
    1.66
    特に
    1.63
    Especially
    1.63
     особливо
    1.61
    particularly
    1.60
    Activations Density 0.849%

    No Known Activations