© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5041
    Prev
    Next
    INDEX
    Explanations

    such

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
     folks
    0.74
     Yep
    0.68
     mom
    0.67
     cuz
    0.66
    -->
    0.66
    下面的
    0.66
     меньше
    0.65
    얘
    0.65
    ->
    0.64
     huh
    0.64
    POSITIVE LOGITS
     such
    3.41
     Such
    3.10
    Such
    3.08
    such
    2.98
     SUCH
    2.62
     چنین
    1.98
     telles
    1.97
     таких
    1.94
     такую
    1.92
     такие
    1.87
    Activations Density 0.551%

    No Known Activations