© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3975
    Prev
    Next
    INDEX
    Explanations

    options or substitutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ین
    1.85
    ل
    1.82
    ینا
    1.55
    ंग
    1.52
    ა
    1.52
    el
    1.48
    ল
    1.44
    م
    1.42
    نوع
    1.39
    ર
    1.39
    POSITIVE LOGITS
     의해
    1.43
     eléctricos
    1.27
    ванні
    1.27
     ánh
    1.22
     인한
    1.20
     인해
    1.19
    㐄
    1.19
     pulverized
    1.16
     Therapeut
    1.15
    evi
    1.12
    Activations Density 0.020%

    No Known Activations