Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12560
    Prev
    Next
    INDEX
    Explanations

    appeal to, unlike sugars

    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_16k_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
     jähr
    0.44
    تميز
    0.44
     অমর
    0.43
    ㄡ
    0.43
     Vier
    0.42
     bestimmte
    0.42
     intensidad
    0.42
     চলুন
    0.42
     canción
    0.42
    郷
    0.42
    POSITIVE LOGITS
     tweaks
    0.50
     calculations
    0.49
     mats
    0.48
     calculation
    0.47
     infographics
    0.46
     wages
    0.46
    explain
    0.45
     impression
    0.44
    impression
    0.44
     strips
    0.44
    Activations Density 0.035%

    No Known Activations