© 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. 1896
    Prev
    Next
    INDEX
    Explanations

    fundamental concepts

    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
    ت
    1.76
    ه
    1.58
    er
    1.39
    a
    1.38
    ம்
    1.35
    ли
    1.32
     TERMS
    1.25
    y
    1.25
    د
    1.24
    లో
    1.24
    POSITIVE LOGITS
    િન
    1.34
    
    1.29
    referenced
    1.22
     oth
    1.21
    ová
    1.20
     گیری
    1.15
    slateg
    1.14
    mong
    1.13
     amplification
    1.12
     tsy
    1.12
    Activations Density 0.068%

    No Known Activations