© 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-262K
    7. 12036
    Prev
    Next
    INDEX
    Explanations

    Sarah and fatigue

    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_262k_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
    ت
    4.38
    ल
    4.20
    a
    3.94
    ০
    3.90
    на
    3.80
    y
    3.58
    tant
    3.50
    ق
    3.40
    ת
    3.34
    ה
    3.09
    POSITIVE LOGITS
     functors
    3.29
    FlightID
    3.00
    ্ধ্য
    2.99
    ૃતિ
    2.87
    으로는
    2.83
     imposed
    2.76
    શ
    2.72
    ?!?
    2.71
     accede
    2.60
    lectual
    2.55
    Activations Density 0.071%

    No Known Activations