© 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. 1693
    Prev
    Next
    INDEX
    Explanations

    how to

    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
     noqa
    1.68
    descripcion
    1.65
    igual
    1.64
     zonal
    1.57
    אות
    1.57
     sunt
    1.51
    ן
    1.50
    젖
    1.49
    কে
    1.47
    اس
    1.47
    POSITIVE LOGITS
    the
    1.71
    ும்போது
    1.58
    
    1.49
     कड़ी
    1.42
     acidified
    1.41
     vya
    1.39
    பி
    1.38
    ッグ
    1.37
     the
    1.36
     причем
    1.35
    Activations Density 0.249%

    No Known Activations