© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17409
    Prev
    Next
    INDEX
    Explanations

    but and contrast

    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
     እነ
    0.45
     জনের
    0.44
    嬋
    0.43
    età
    0.42
     Kardash
    0.42
     ሰው
    0.42
    ப்பட்டு
    0.41
     Elvis
    0.41
     basename
    0.41
     Якщо
    0.41
    POSITIVE LOGITS
    ↵
    0.47
    US
    0.45
    AS
    0.42
    </h2>
    0.41
    IT
    0.41
    ADI
    0.40
    吉
    0.39
     lia
    0.38
    WiFi
    0.38
    ↵↵
    0.38
    Activations Density 0.039%

    No Known Activations