© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 139680
    Prev
    Next
    INDEX
    Explanations

    energy barrier

    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
    ﻨ
    0.59
    nomina
    0.57
    ﯿ
    0.55
    ﺨ
    0.53
    ma
    0.52
    priority
    0.49
    refund
    0.49
    proportion
    0.48
    pled
    0.48
    veren
    0.48
    POSITIVE LOGITS
     rejuvenated
    0.59
     contactless
    0.56
     new
    0.54
     #
    0.54
     encapsulates
    0.53
     recente
    0.52
     /
    0.52
     reinvigor
    0.52
     Edit
    0.51
     dà
    0.51
    Activations Density 0.002%

    No Known Activations