© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2389
    Prev
    Next
    INDEX
    Explanations

    python file reading .txt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ाइवेट
    1.28
    轳
    1.28
    این
    1.21
    ის
    1.20
    larında
    1.20
    ް
    1.20
    梸
    1.18
     soaring
    1.17
    toolStrip
    1.17
     ନ
    1.15
    POSITIVE LOGITS
     glanced
    1.01
     작성
    0.98
    entes
    0.93
    ish
    0.92
    ض
    0.92
     wider
    0.92
     Jesus
    0.92
     Equals
    0.91
     argument
    0.91
     text
    0.90
    Activations Density 0.528%

    No Known Activations