© 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. 36236
    Prev
    Next
    INDEX
    Explanations

    mathematical or physical properties

    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
    ary
    1.69
    ע
    1.66
    ır
    1.59
    ל
    1.58
    ic
    1.57
    ח
    1.46
    ud
    1.34
    and
    1.32
    p
    1.32
    в
    1.32
    POSITIVE LOGITS
    ፣
    1.58
    ،
    1.56
    可以使用
    1.39
     публику
    1.28
    可以用
    1.27
     др
    1.26
     конечно
    1.24
     можа
    1.23
    ؟
    1.23
    ，《
    1.22
    Activations Density 0.000%

    No Known Activations