© 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. 6813
    Prev
    Next
    INDEX
    Explanations

    numbered steps and sequences

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

    option 1

    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
     થય
    0.46
     seduced
    0.41
    rendered
    0.41
    िंग्स
    0.41
     voire
    0.40
    မည်
    0.38
    曛
    0.37
    ዚህ
    0.37
    vintage
    0.36
     ক্ষমতা
    0.36
    POSITIVE LOGITS
     pertama
    1.07
    Ⅰ
    1.01
     पहला
    0.94
    １
    0.93
     первый
    0.90
     первом
    0.87
     primeira
    0.86
     первая
    0.86
     первое
    0.86
     första
    0.84
    Activations Density 0.050%

    No Known Activations