© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23839
    Prev
    Next
    INDEX
    Explanations

    with, along, plus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    ,?
    0.47
    ،
    0.45
     bliver
    0.45
     régulièrement
    0.44
     correctement
    0.43
     hingegen
    0.43
    ЕЛ
    0.42
    ネ
    0.41
     properly
    0.41
    .$,
    0.41
    POSITIVE LOGITS
     وذلك
    0.50
    featuring
    0.47
     sodass
    0.46
     साथ
    0.45
     beserta
    0.44
     along
    0.43
    spersed
    0.43
     עם
    0.43
     plus
    0.42
     to
    0.41
    Activations Density 0.002%

    No Known Activations