© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1571
    Prev
    Next
    INDEX
    Explanations

    document headers

    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_22_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
     Here
    0.99
     Let
    0.91
     firstly
    0.91
     ValueTask
    0.90
     Veamos
    0.89
     Firstly
    0.89
     ①
    0.88
     собственно
    0.88
    ១
    0.86
     Berikut
    0.86
    POSITIVE LOGITS
    Subject
    0.86
    Date
    0.85
    Status
    0.84
    Subjects
    0.82
    Printed
    0.78
    subject
    0.77
    Copyright
    0.76
    Type
    0.72
    date
    0.72
    FOV
    0.72
    Activations Density 0.161%

    No Known Activations