© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 4664
    Prev
    Next
    INDEX
    Explanations

    introducing definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     С
    1.07
     ي
    1.03
     ل
    1.01
     У
    1.01
     لت
    1.00
     بال
    0.98
     الم
    0.95
     C
    0.95
     не
    0.93
     с
    0.92
    POSITIVE LOGITS
    িয়৷
    1.04
     တော့
    1.00
     labbhati
    1.00
    <unused851>
    1.00
     vutto
    0.99
     শুক্রাচার্য
    0.98
    डिज
    0.97
     गरी
    0.96
    。.
    0.96
     ಏ
    0.95
    Activations Density 0.170%

    No Known Activations