© 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. 51316
    Prev
    Next
    INDEX
    Explanations

    budget and formality explanations

    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
     children
    0.49
     nuovi
    0.46
    0.46
     cleats
    0.43
     t
    0.43
     kids
    0.43
     creative
    0.43
     mothers
    0.43
     novos
    0.42
     therapeutic
    0.42
    POSITIVE LOGITS
     शो
    0.53
    𝐧
    0.51
    ्यक्रम
    0.50
    ፦
    0.49
    ควบคุม
    0.47
    াবাদের
    0.46
    Etudes
    0.46
    ร์
    0.46
    лены
    0.46
     ක්‍ර
    0.46
    Activations Density 0.020%

    No Known Activations