© 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. 12803
    Prev
    Next
    INDEX
    Explanations

    turtle graphics

    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
     buradan
    1.35
     trabalhadores
    1.32
     neutrinos
    1.31
     isomorphisms
    1.30
    étera
    1.28
    <unused1936>
    1.27
     screws
    1.27
    近年来
    1.26
    अय
    1.25
    হাম্মদ
    1.24
    POSITIVE LOGITS
    ed
    1.09
    ej
    1.02
    anz
    0.99
    된
    0.97
    ::-
    0.97
    γε
    0.95
    ேக
    0.94
     gez
    0.92
    ANZ
    0.90
    tions
    0.89
    Activations Density 0.008%

    No Known Activations