© 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-262K
    7. 11127
    Prev
    Next
    INDEX
    Explanations

    game engine names

    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_262k_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
    ی
    1.65
    %';
    1.57
    ை
    1.40
    महाराष्ट्र
    1.36
    ploidy
    1.36
     Förder
    1.35
    chließlich
    1.34
    nCurrent
    1.33
    й
    1.32
     ''),
    1.32
    POSITIVE LOGITS
     sanguí
    1.32
    of
    1.31
     의한
    1.29
    
    1.28
     afirm
    1.26
     reap
    1.24
    boldsymbol
    1.24
    cule
    1.24
     ocasion
    1.24
    Alz
    1.23
    Activations Density 0.001%

    No Known Activations