© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5777
    Prev
    Next
    INDEX
    Explanations

    grass and grasslands

    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_17_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
     отверсти
    1.47
     Vessels
    1.46
     refrigerated
    1.44
     volcanic
    1.41
     magnetite
    1.39
    
    1.39
     penetrate
    1.38
    य
    1.38
     typhoid
    1.37
     pisc
    1.36
    POSITIVE LOGITS
    蜢
    2.02
    ed
    1.56
    ies
    1.53
    دخل
    1.46
    s
    1.42
    hopper
    1.41
    sam
    1.41
    sz
    1.40
    Rewrite
    1.38
    sing
    1.37
    Activations Density 0.089%

    No Known Activations