© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200102
    Prev
    Next
    INDEX
    Explanations

    corporations offer, father, thought process

    np_acts-logits-general · gemini-2.5-flash-lite

    dividing into smaller

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    op
    0.58
    params
    0.56
    ि
    0.54
    zahlung
    0.53
    inplace
    0.52
    ος
    0.52
    copies
    0.52
    fail
    0.52
    item
    0.51
    li
    0.50
    POSITIVE LOGITS
    之道
    0.43
    疑
    0.42
    뽀
    0.42
     monot
    0.42
    的发展
    0.41
    枃
    0.41
    삼성
    0.41
     problemática
    0.40
    버
    0.40
    疑问
    0.40
    Activations Density 0.001%

    No Known Activations