© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5773
    Prev
    Next
    INDEX
    Explanations

    documentation formatting

    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_17_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
    ein
    0.78
     যেটা
    0.72
    eit
    0.70
     लेख
    0.69
     Chil
    0.69
    sang
    0.68
    e
    0.68
    eip
    0.66
     article
    0.66
     తీ
    0.64
    POSITIVE LOGITS
     වර්ග
    0.97
    ̹
    0.91
    ബന്ധ
    0.86
     baseApiPath
    0.85
    ।'
    0.84
     阅读全文
    0.84
     rampant
    0.83
     subjug
    0.83
     tyranny
    0.81
    .''
    0.81
    Activations Density 0.101%

    No Known Activations