© 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. 2515
    Prev
    Next
    INDEX
    Explanations

    artificial general intelligence

    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
    ы
    2.54
    sar
    2.29
     уж
    2.27
     respetar
    2.12
    т
    2.12
    ي
    2.02
    你需要
    2.01
    €™
    2.01
    heartedly
    2.00
    берите
    1.98
    POSITIVE LOGITS
    is
    3.57
    ဟုတ်
    2.56
    و
    2.56
    ीकरण
    2.36
     chromatography
    2.23
    ని
    2.13
     absenteeism
    2.11
     Chromatography
    2.10
     Amendments
    2.07
     refinery
    2.06
    Activations Density 0.135%

    No Known Activations