© 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. 96725
    Prev
    Next
    INDEX
    Explanations

    for example

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

    position themselves, acting as

    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
     grosseur
    0.46
    玩具
    0.44
    Mw
    0.43
    FJ
    0.43
    MZ
    0.43
    玤
    0.43
    роприя
    0.41
    米
    0.41
     १३
    0.41
    ционным
    0.41
    POSITIVE LOGITS
     подоб
    0.49
     সূত্র
    0.44
    jenje
    0.44
     Gutierrez
    0.44
     dalla
    0.44
     Forrest
    0.42
    illing
    0.41
    ிற்று
    0.41
     Seah
    0.40
     Otter
    0.40
    Activations Density 0.001%

    No Known Activations