© 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. 1851
    Prev
    Next
    INDEX
    Explanations

    show videos

    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
    ه
    3.00
    ী
    2.99
    ur
    2.95
     شك
    2.89
    ية
    2.88
    ال
    2.84
    러스
    2.83
    ulation
    2.78
    வா
    2.78
    𝗈
    2.76
    POSITIVE LOGITS
    唆
    3.39
    ت
    3.27
    stopping
    3.23
    犸
    3.10
    AsAction
    3.09
    stopper
    2.84
     conclusively
    2.72
    razioni
    2.69
    म्या
    2.66
    tuvo
    2.63
    Activations Density 0.300%

    No Known Activations