© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5533
    Prev
    Next
    INDEX
    Explanations

    words starting with el

    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_22_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
    ották
    0.71
     totality
    0.69
    ل
    0.67
    ទាំង
    0.65
    ták
    0.65
    ت
    0.65
    y
    0.64
    RootNamespace
    0.64
    d
    0.63
    yld
    0.62
    POSITIVE LOGITS
    aboration
    1.06
     ouvrages
    0.89
    éments
    0.88
     народного
    0.86
     avance
    0.86
     uur
    0.84
     Oekra
    0.84
    ixir
    0.83
     ड
    0.83
    ías
    0.80
    Activations Density 0.016%

    No Known Activations