© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65596
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    similarity and comparison

    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
    }\,\
    0.36
     archipelago
    0.34
     روز
    0.33
    azzi
    0.33
     protokol
    0.33
    chronic
    0.32
    anjana
    0.32
    ズル
    0.32
    }\,
    0.32
     sectoral
    0.32
    POSITIVE LOGITS
    同樣
    0.42
    也可以
    0.39
    同样
    0.37
    下一个
    0.36
     hingegen
    0.36
     दूसरा
    0.35
    也會
    0.35
     natomiast
    0.35
    同样的
    0.35
    也能
    0.34
    Activations Density 0.968%

    No Known Activations