© 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. 191657
    Prev
    Next
    INDEX
    Explanations

    data portability and privacy rights

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

    managing processes and logistics

    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
     atak
    0.56
     柄
    0.56
     กําลัง
    0.54
    manip
    0.52
     ニット
    0.52
     trov
    0.51
     amaç
    0.51
     Rodr
    0.51
     julg
    0.51
     cujo
    0.50
    POSITIVE LOGITS
    Electron
    0.47
    >("
    0.45
    若干
    0.45
    кси
    0.44
    两种
    0.42
    关于
    0.42
    许多
    0.42
    vyšší
    0.41
    两大
    0.41
    足够
    0.41
    Activations Density 0.000%

    No Known Activations