© 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. 31-GEMMASCOPE-2-RES-65K
    7. 50146
    Prev
    Next
    INDEX
    Explanations

    phrases for correction and formality

    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
    pośred
    0.44
     اجتماعی
    0.43
     distingu
    0.42
     panggilan
    0.42
     socials
    0.42
    </h2>
    0.41
     sociali
    0.41
     disponibili
    0.41
     superiores
    0.40
     affaires
    0.40
    POSITIVE LOGITS
    ஷ்
    0.49
     shift
    0.45
     hexadecimal
    0.43
    >$
    0.42
    路
    0.42
     waved
    0.42
     beep
    0.42
    าค
    0.42
    urous
    0.41
     chime
    0.41
    Activations Density 0.003%

    No Known Activations