© 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. 15231
    Prev
    Next
    INDEX
    Explanations

    ads, budget, but, because, directly

    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
     conjunct
    0.42
    INTRODUCTION
    0.41
    煞
    0.41
    CHAPTER
    0.40
     Introduction
    0.40
    愁
    0.39
    ahiye
    0.39
    Introduction
    0.39
     indistinct
    0.37
    <unused32>
    0.37
    POSITIVE LOGITS
    ads
    0.44
     ads
    0.43
     budgets
    0.42
     Ads
    0.40
    Cabin
    0.40
    Ads
    0.40
    ‶
    0.40
     व्ही
    0.39
     Tops
    0.39
    Ad
    0.38
    Activations Density 0.002%

    No Known Activations