© 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. 41412
    Prev
    Next
    INDEX
    Explanations

    handle, info, mountains, script

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

    work-related tasks and scheduling

    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
    支出
    0.42
    Share
    0.40
     disguise
    0.39
    rizona
    0.38
    ภ
    0.38
    cka
    0.38
     disguised
    0.37
    भाग्य
    0.37
    几次
    0.37
    考察
    0.37
    POSITIVE LOGITS
     Sinhalese
    0.51
    安静
    0.51
     lLoginID
    0.51
     Tây
    0.48
     Dong
    0.48
     Scrib
    0.48
    ０
    0.47
     Clín
    0.46
     Insel
    0.46
     Bildschirm
    0.46
    Activations Density 0.000%

    No Known Activations