© 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-16K
    7. 12893
    Prev
    Next
    INDEX
    Explanations

    type checking and conversion

    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_16k_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
    AL
    1.03
    CHES
    0.98
    ER
    0.96
    il
    0.95
    ция
    0.88
    HAN
    0.88
    2
    0.88
    HN
    0.88
    ম্প
    0.87
    RO
    0.86
    POSITIVE LOGITS
    。
    1.17
    💴
    1.07
    飢
    0.95
    返回
    0.92
     lím
    0.90
     That
    0.90
    하면서
    0.90
     Lill
    0.90
     Daim
    0.89
     رنگ
    0.88
    Activations Density 0.249%

    No Known Activations