© 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. 175025
    Prev
    Next
    INDEX
    Explanations

    following 'doing so'

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

    how to make estimates

    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
     avec
    0.52
    平时
    0.50
    我們可以
    0.50
    ˦
    0.49
     ইনডাকশন
    0.47
    伙
    0.47
    ˢ
    0.47
     করাই
    0.46
    烘
    0.46
     ਮ
    0.46
    POSITIVE LOGITS
    ,</
    0.46
     debunk
    0.42
     sovere
    0.42
     meliputi
    0.41
     sovereign
    0.40
    dis
    0.39
    discovered
    0.39
    free
    0.38
     formulae
    0.38
     discovering
    0.38
    Activations Density 0.007%

    No Known Activations