© 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. 165818
    Prev
    Next
    INDEX
    Explanations

    backup, transfer, Print, steal

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

    Minimum Spanning Forest

    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
    की
    0.54
    гли
    0.53
    ди
    0.52
    л
    0.52
    на
    0.50
    ጾ
    0.49
    т
    0.48
    면
    0.46
    ות
    0.45
    тру
    0.45
    POSITIVE LOGITS
     đau
    0.53
     circumstances
    0.52
     diarrh
    0.51
     程序
    0.50
     ଚ
    0.50
     brunâtre
    0.49
     "'";
    0.48
     দৃষ্ট
    0.48
     considerato
    0.48
    ্থিত
    0.48
    Activations Density 0.000%

    No Known Activations