© 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. 25863
    Prev
    Next
    INDEX
    Explanations

    other things or roles

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

    stick controls

    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
     oftentimes
    0.39
     möglicherweise
    0.38
     fortitude
    0.37
    NOTA
    0.37
    ޢ
    0.37
     bądź
    0.36
    بعض
    0.36
     verrà
    0.36
     customarily
    0.36
    роятно
    0.35
    POSITIVE LOGITS
     브
    0.52
    加上
    0.51
    那边
    0.47
     গ্রুপ
    0.45
    侧
    0.45
    linge
    0.45
     плюс
    0.45
     tuple
    0.44
    两个
    0.44
     옆
    0.43
    Activations Density 0.000%

    No Known Activations