© 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. 31-GEMMASCOPE-2-RES-65K
    7. 52053
    Prev
    Next
    INDEX
    Explanations

    scheduling, generating, accelerating, simulating

    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_31_width_65k_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
    𝐠
    0.50
     पढ
    0.48
    𝐥
    0.47
     polypropylene
    0.45
    ání
    0.44
    blog
    0.44
     intimidation
    0.43
    ád
    0.43
    一
    0.43
     كتابه
    0.42
    POSITIVE LOGITS
    ות
    0.57
    )
    0.53
    ایات
    0.53
    ئة
    0.49
    امات
    0.47
     chacun
    0.46
    רג
    0.46
     wakeup
    0.46
    radas
    0.46
     Nucl
    0.44
    Activations Density 0.003%

    No Known Activations