© 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. 11611
    Prev
    Next
    INDEX
    Explanations

    descriptive, adaptive, predictive

    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
    т
    4.48
    ers
    4.42
    ো
    3.27
    са
    3.18
    িল
    3.10
    л
    3.02
    ier
    2.92
    ли
    2.91
    ation
    2.88
    딴
    2.85
    POSITIVE LOGITS
     будем
    3.04
    겐
    2.99
    IÓN
    2.93
    StringVar
    2.89
    cento
    2.84
    y
    2.81
    ReferencePose
    2.81
    glich
    2.77
    класс
    2.75
    ksi
    2.73
    Activations Density 0.365%

    No Known Activations