© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1777
    Prev
    Next
    INDEX
    Explanations

    faster than HDDs

    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_22_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
     സംഭവ
    0.73
    ಲಭ
    0.65
    ">+</
    0.63
    ccin
    0.62
    йт
    0.62
     soit
    0.60
    Pued
    0.59
    ेटेड
    0.59
     gesprek
    0.58
     stehen
    0.58
    POSITIVE LOGITS
     autrefois
    3.03
     formerly
    2.98
     سابقا
    2.94
     old
    2.90
     tidligere
    2.90
     originally
    2.86
     previous
    2.86
    昔
    2.80
    曾经
    2.77
     tidigare
    2.76
    Activations Density 1.798%

    No Known Activations