© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35698
    Prev
    Next
    INDEX
    Explanations

    SQL constraint keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     লিঙ্ক
    0.40
    ぞ
    0.38
    ವಲ್ಲ
    0.38
    ೆಂ
    0.38
    ഴും
    0.37
    Ｚ
    0.37
    縊
    0.37
     Blackhawks
    0.37
     çözüm
    0.36
     हेनरी
    0.36
    POSITIVE LOGITS
     thủ
    0.38
    _.
    0.38
    criptor
    0.36
    _$
    0.36
     Peak
    0.36
     voy
    0.36
    ோ
    0.36
     собственно
    0.35
     верши
    0.35
     wr
    0.35
    Activations Density 0.000%

    No Known Activations