© 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. 2270
    Prev
    Next
    INDEX
    Explanations

    dive into

    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
    ر
    4.65
    er
    3.97
    leşt
    2.87
    い
    2.83
    erent
    2.79
    alities
    2.74
    ための
    2.74
    ীষ্ম
    2.74
    UINT
    2.72
    它
    2.69
    POSITIVE LOGITS
    ма
    2.94
    िक
    2.93
     తొ
    2.92
    aking
    2.92
    ला
    2.83
    ч
    2.83
     lume
    2.77
     Considerable
    2.73
    ensitive
    2.64
     colourful
    2.63
    Activations Density 0.294%

    No Known Activations