© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10898
    Prev
    Next
    INDEX
    Explanations

    css color value #ccc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     राठ
    2.23
    .([]
    2.01
    蔔
    1.98
     Props
    1.98
    猗
    1.93
    侖
    1.92
    င
    1.92
     कमलेश
    1.90
    ίων
    1.90
     सुरेश
    1.89
    POSITIVE LOGITS
     passing
    1.90
    पास
    1.75
    तौर
    1.71
     wet
    1.71
     mier
    1.67
     namesake
    1.65
     m
    1.63
    Ist
    1.63
    一面
    1.62
    नाम
    1.57
    Activations Density 0.061%

    No Known Activations