© 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. 83811
    Prev
    Next
    INDEX
    Explanations

    provocative work

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

    ultimate triumph

    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
     రా
    0.49
     ప్రారంభ
    0.47
     разрабаты
    0.47
    আত্ম
    0.46
     Wärme
    0.46
     নকল
    0.46
     דר
    0.45
     發
    0.45
     conquering
    0.44
    lebn
    0.44
    POSITIVE LOGITS
    el
    0.55
    vu
    0.51
    Can
    0.48
    ones
    0.47
     that
    0.47
    is
    0.47
    𝑓
    0.47
    ALES
    0.46
    alities
    0.45
    BU
    0.45
    Activations Density 0.000%

    No Known Activations