© 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. 42003
    Prev
    Next
    INDEX
    Explanations

    foreign numbers and phrases

    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
    ラ
    1.00
    ed
    1.00
    ت
    0.96
    驱
    0.96
     stayed
    0.92
     advers
    0.90
    চু
    0.90
    '(
    0.89
     instituted
    0.89
     stepwise
    0.89
    POSITIVE LOGITS
    ารย์
    1.18
    ri
    1.16
     fenêtre
    1.12
    punkt
    1.11
    nya
    1.08
    นี้
    1.08
     vão
    1.05
    0
    1.02
    bem
    1.00
    ным
    0.99
    Activations Density 0.000%

    No Known Activations