© 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. 1237
    Prev
    Next
    INDEX
    Explanations

    property and ownership

    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
    ה
    3.18
    له
    2.90
    цкі
    2.67
    ार्किक
    2.65
    もの
    2.58
    kker
    2.54
    𝖗
    2.52
    ेक्ट
    2.50
    𝕋
    2.49
     ByteBuffer
    2.46
    POSITIVE LOGITS
    ו
    4.87
    tied
    3.38
    oare
    2.97
    خدام
    2.92
    र
    2.79
    有的
    2.71
    ي
    2.70
     ellipsis
    2.61
    affiche
    2.59
     aprovechar
    2.57
    Activations Density 0.722%

    No Known Activations