© 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. 29-GEMMASCOPE-2-RES-65K
    7. 2649
    Prev
    Next
    INDEX
    Explanations

    ten, range, quantities

    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_29_width_65k_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
    Fourth
    0.65
     第
    0.62
     pharetra
    0.60
    旲
    0.59
    第
    0.59
    Desde
    0.59
    Weekday
    0.58
     চতুর্থ
    0.57
     tweede
    0.57
    Double
    0.57
    POSITIVE LOGITS
     ten
    1.35
     six
    1.04
     TEN
    1.03
    ten
    1.02
     five
    1.01
     nine
    0.98
    TEN
    0.96
     десять
    0.96
    🔟
    0.92
    five
    0.90
    Activations Density 0.375%

    No Known Activations