© 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. 1516
    Prev
    Next
    INDEX
    Explanations

    words starting with t

    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
    اً
    4.89
    l
    4.70
    u
    4.40
    y
    4.31
    ки
    4.07
    h
    4.01
    م
    4.00
    ۰
    3.93
    j
    3.90
    r
    3.89
    POSITIVE LOGITS
    таю
    2.80
    та
    2.72
     biosolids
    2.67
     eyebrows
    2.60
     vegetative
    2.58
     insolvency
    2.58
    ┈┈
    2.46
    queous
    2.45
    र्गत
    2.43
     hạn
    2.40
    Activations Density 0.375%

    No Known Activations