© 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-262K
    7. 9781
    Prev
    Next
    INDEX
    Explanations

    visual designer

    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
    an
    1.63
    ल्लभ
    1.47
    𝑒
    1.45
    ا
    1.43
     زائد
    1.40
    ת
    1.38
    a
    1.31
    тата
    1.24
     Hochsch
    1.23
    ാ
    1.23
    POSITIVE LOGITS
    shown
    1.61
    Chile
    1.58
    strictly
    1.57
    ׁ
    1.56
    ことができます
    1.56
    ্পনিক
    1.55
    redu
    1.55
    water
    1.51
    melt
    1.50
     occurring
    1.50
    Activations Density 0.000%

    No Known Activations