© 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. 21601
    Prev
    Next
    INDEX
    Explanations

    social event or Integer

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

    code structures and technical terms

    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
    ются
    0.43
     تقديم
    0.41
     mankind
    0.41
    ли
    0.40
     병
    0.40
     ကျွန်
    0.40
     Mankind
    0.39
     پر
    0.38
     男
    0.38
     bizim
    0.38
    POSITIVE LOGITS
     RDA
    0.52
    इसका
    0.46
     camin
    0.45
     τραγ
    0.44
    전히
    0.43
     उसका
    0.43
    nue
    0.43
    नाक
    0.43
     daughters
    0.42
     уроке
    0.42
    Activations Density 0.000%

    No Known Activations