© 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. 208687
    Prev
    Next
    INDEX
    Explanations

    federal; returned; Gospel; ideal

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

    weakening, weak, location, without

    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
    کا
    0.50
    只好
    0.50
    پ
    0.45
     zasi
    0.44
    ك
    0.44
     পেল
    0.43
     সিটি
    0.43
     فلسطینی
    0.42
     nowych
    0.42
    ቸውን
    0.42
    POSITIVE LOGITS
    emit
    0.51
     errors
    0.50
     Authentication
    0.50
    u
    0.47
    iav
    0.47
    l
    0.47
     Issued
    0.45
    惰
    0.45
    依旧
    0.45
     mediums
    0.45
    Activations Density 0.000%

    No Known Activations