© 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-16K
    7. 11738
    Prev
    Next
    INDEX
    Explanations

    emphasizing specific details

    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_31_width_16k_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
     other
    0.68
    その他
    0.63
    O
    0.63
     merely
    0.60
     a
    0.59
    ほか
    0.59
     உட்பட
    0.59
    :
    0.59
    其他的
    0.58
     simplesmente
    0.58
    POSITIVE LOGITS
     Particularly
    0.96
     besonders
    0.93
     Especially
    0.91
     wenn
    0.90
     특히
    0.87
    尤其是
    0.82
    Especially
    0.82
     özellikle
    0.80
     Özellikle
    0.79
     особенно
    0.78
    Activations Density 0.224%

    No Known Activations