© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 930
    Prev
    Next
    INDEX
    Explanations

    family and company members

    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
    сиз
    1.01
    ꜱ
    1.01
    NORM
    0.99
    ონის
    0.94
     "";
    0.92
    ำ
    0.91
    מ
    0.91
    隷
    0.91
    );}
    0.91
     العافيه
    0.91
    POSITIVE LOGITS
    们的
    1.23
    क
    1.03
    speople
    1.02
    वृत्ति
    0.97
    are
    0.97
     iu
    0.95
    تى
    0.94
     foco
    0.94
    unter
    0.91
    دل
    0.88
    Activations Density 0.368%

    No Known Activations