© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 144070
    Prev
    Next
    INDEX
    Explanations

    The Weeknd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AR
    1.21
    ER
    1.18
    er
    1.15
    AG
    1.12
    AN
    1.08
    f
    1.08
    v
    1.06
    n
    1.02
    A
    1.00
    es
    0.96
    POSITIVE LOGITS
    ни
    1.06
    ке
    0.96
    це
    0.87
     alegr
    0.85
    тур
    0.84
     niej
    0.82
     lực
    0.80
     ejecutar
    0.79
     exigir
    0.79
     ayudarte
    0.78
    Activations Density 0.003%

    No Known Activations