© 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. 74163
    Prev
    Next
    INDEX
    Explanations

    may enable

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

    SQL query structure

    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
    ।
    0.55
    。
    0.54
    ،
    0.45
    ።
    0.44
    。.
    0.44
    賴
    0.43
    。,
    0.43
    gué
    0.42
    INEN
    0.41
     ところ
    0.41
    POSITIVE LOGITS
     showcased
    0.49
    จะมี
    0.46
    带来了
    0.45
     એક
    0.45
    会出现
    0.44
    进行了
    0.44
     Cinematic
    0.43
    🎬
    0.43
     Delivering
    0.42
    构建
    0.42
    Activations Density 0.000%

    No Known Activations