© 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. 73106
    Prev
    Next
    INDEX
    Explanations

    Zayn Malik

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

    enthusiasm and excitement

    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
    D
    0.50
    Pictures
    0.47
    ঙ্কর
    0.45
    DI
    0.45
    ibu
    0.45
    DW
    0.45
     ordinairement
    0.44
     ખાસ
    0.44
     غیر
    0.43
    editar
    0.43
    POSITIVE LOGITS
    innovation
    0.49
    籵
    0.49
    瓄
    0.47
    ิลป
    0.46
    సిన
    0.45
    醚
    0.45
    spin
    0.45
    轵
    0.43
     spin
    0.43
    tho
    0.43
    Activations Density 0.000%

    No Known Activations