© 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. 59477
    Prev
    Next
    INDEX
    Explanations

    difference between

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

    Beginner's Luck

    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
    ad
    0.52
    ↵↵
    0.50
    eff
    0.50
    p
    0.50
     Prakt
    0.48
    node
    0.48
    add
    0.47
     prakt
    0.47
    fer
    0.46
     menampilkan
    0.46
    POSITIVE LOGITS
     чыныгы
    0.52
    ाइव
    0.51
    ᾿
    0.51
    кономи
    0.50
    निज
    0.50
    тися
    0.49
    㳡
    0.49
    𝑉
    0.48
    ριν
    0.47
    тріш
    0.47
    Activations Density 0.000%

    No Known Activations