© 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-262K
    7. 10770
    Prev
    Next
    INDEX
    Explanations

    intent recognition and classification

    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
    к
    4.02
    ה
    3.35
    st
    3.33
    o
    3.07
     zato
    2.72
     dựng
    2.72
    k
    2.71
     herd
    2.64
    ্যান্ড
    2.62
    r
    2.60
    POSITIVE LOGITS
    想不到
    2.92
    ळे
    2.89
    ळ
    2.78
     sweetener
    2.78
    NEL
    2.77
     palab
    2.71
    IONAL
    2.66
    াবির
    2.60
    кий
    2.59
     flavonoids
    2.58
    Activations Density 0.027%

    No Known Activations