© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42208
    Prev
    Next
    INDEX
    Explanations

    names followed by et al

    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
     Sự
    1.07
    lcd
    1.04
     Интере
    1.03
    据悉
    1.00
    yaratan
    0.99
    場合には
    0.98
     從
    0.98
    czne
    0.98
     Многие
    0.98
     Eropa
    0.97
    POSITIVE LOGITS
    ada
    1.13
     ada
    1.07
     modific
    1.00
    ta
    0.97
    ten
    0.96
    ان
    0.94
     mir
    0.93
    q
    0.92
     mana
    0.92
    ts
    0.90
    Activations Density 0.001%

    No Known Activations