© 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. 156927
    Prev
    Next
    INDEX
    Explanations

    following days

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

    numbered list

    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
    看得
    0.53
    ផ្ត
    0.47
    Saldo
    0.46
    相应的
    0.45
    ﭼ
    0.44
    转发
    0.43
    InBackground
    0.43
    对外
    0.43
     flushed
    0.43
    Miami
    0.43
    POSITIVE LOGITS
     코로나
    0.51
     다섯
    0.50
     contest
    0.48
     dụng
    0.47
     соревнования
    0.47
     लेखन
    0.46
     readership
    0.46
     competition
    0.45
     competitions
    0.45
     ὑ
    0.45
    Activations Density 0.001%

    No Known Activations