© 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. 107556
    Prev
    Next
    INDEX
    Explanations

    pertain to, because, robust economy

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

    education, NVIDIA, Rome, origins

    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
    ೆಯ
    0.45
     Elektrokhimiya
    0.45
     ಉತ್ತರ
    0.44
    urés
    0.43
    Ζ
    0.43
    ADE
    0.43
     ছাত্রী
    0.42
     สาว
    0.41
    <unused16>
    0.41
    ΟΣ
    0.41
    POSITIVE LOGITS
     wrought
    0.42
     proactively
    0.41
    怯
    0.41
     disposiciones
    0.39
     revoc
    0.38
    ldon
    0.38
     inodes
    0.37
    主动
    0.36
    張り
    0.35
     inconce
    0.35
    Activations Density 0.003%

    No Known Activations