© 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. 2467
    Prev
    Next
    INDEX
    Explanations

    okay,

    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
    মন
    0.86
    鰓
    0.79
     foils
    0.78
     estabelecer
    0.78
     ನೀ
    0.75
    holen
    0.75
    ⼊
    0.73
     ነ
    0.73
    設立
    0.72
    ḡ
    0.71
    POSITIVE LOGITS
     bandas
    0.66
     Tiere
    0.65
    Mw
    0.62
    kh
    0.59
    Ug
    0.59
     Zamb
    0.59
    ry
    0.58
    ක්‍
    0.58
     Uganda
    0.58
     Dis
    0.58
    Activations Density 0.090%

    No Known Activations