© 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. 1791
    Prev
    Next
    INDEX
    Explanations

    categories and filters

    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
    ers
    2.98
    ು
    2.94
    tense
    2.88
    traj
    2.81
     temas
    2.68
    ınıza
    2.57
    を図
    2.57
    ění
    2.56
    ところに
    2.55
    ant
    2.52
    POSITIVE LOGITS
    すぐに
    2.96
    紝
    2.80
     azar
    2.72
    pleri
    2.70
    су
    2.62
    𝖒
    2.57
    苓
    2.52
    ו
    2.50
     Hopf
    2.45
    قص
    2.45
    Activations Density 0.395%

    No Known Activations