© 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-16K
    7. 718
    Prev
    Next
    INDEX
    Explanations

    a little, Miss, key, singular

    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
     través
    2.87
     partir
    2.64
    pathetic
    2.36
     priori
    2.31
     veces
    2.23
    hmad
    2.12
     href
    2.07
     d
    2.06
     thousand
    2.06
    जनबी
    2.05
    POSITIVE LOGITS
    l
    3.14
    u
    3.13
    quela
    2.95
    ق
    2.90
    r
    2.69
    is
    2.64
    ف
    2.64
    s
    2.48
    人
    2.45
    ل
    2.42
    Activations Density 0.886%

    No Known Activations