© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 28800
    Prev
    Next
    INDEX
    Explanations

    Tango Festival

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

    device, Fruits, simulation, elephant, awaits

    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
     ener
    0.53
    elf
    0.50
    KIT
    0.50
     oz
    0.49
     deform
    0.48
     ITA
    0.48
    ray
    0.48
     u
    0.47
     additive
    0.47
    ELA
    0.47
    POSITIVE LOGITS
    划分
    0.52
    闓
    0.52
    spacePad
    0.50
    海南
    0.49
    dokkaHtml
    0.48
    结合
    0.47
    ၠ
    0.47
    長の
    0.47
    apaccay
    0.46
    তরাং
    0.46
    Activations Density 0.000%

    No Known Activations