© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 57258
    Prev
    Next
    INDEX
    Explanations

    knowledge

    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
     betrokken
    0.43
    invoke
    0.40
     rozpozn
    0.39
     invoke
    0.38
    深受
    0.38
     tema
    0.37
    established
    0.37
    ጕ
    0.37
     dbo
    0.37
    nf
    0.36
    POSITIVE LOGITS
     knowledge
    1.05
    知识
    0.89
     Knowledge
    0.89
    Knowledge
    0.83
     знания
    0.83
    knowledge
    0.82
    知識
    0.81
     conhecimento
    0.81
     conocimiento
    0.79
     Wissen
    0.79
    Activations Density 0.001%

    No Known Activations