© 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. 24806
    Prev
    Next
    INDEX
    Explanations

    math operations and writing concepts

    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
     schme
    0.43
     molecules
    0.40
     leafy
    0.39
    跶
    0.39
     tubes
    0.39
     psychedelic
    0.39
    ajjati
    0.39
     hippie
    0.38
     salespeople
    0.38
     =&
    0.37
    POSITIVE LOGITS
    ５
    0.61
     ۷
    0.60
     ۱۵
    0.58
     ۵
    0.55
    ８
    0.55
     ৮
    0.55
     ৭
    0.54
     ৫
    0.52
     ১৫
    0.52
     ৬
    0.51
    Activations Density 0.002%

    No Known Activations