© 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. 12013
    Prev
    Next
    INDEX
    Explanations

    Meta's language models

    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
    𝚜
    3.21
    ្សែ
    3.03
    вання
    2.82
    t
    2.82
    tch
    2.78
    𝑑
    2.77
    speaker
    2.74
    ер
    2.67
    siniz
    2.65
    ESS
    2.63
    POSITIVE LOGITS
    ку
    2.95
    eine
    2.86
     abbreviation
    2.81
    
    2.72
    도
    2.71
     PPAR
    2.66
    මාන්
    2.62
    า
    2.61
     tributary
    2.59
    ный
    2.56
    Activations Density 0.007%

    No Known Activations