© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3345
    Prev
    Next
    INDEX
    Explanations

    question words or phrases

    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_16_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
     של
    0.54
    mann
    0.50
    htonl
    0.50
     क्रमश
    0.49
     makes
    0.49
    avil
    0.47
    ântul
    0.47
    ↵↵
    0.46
     את
    0.46
    तरी
    0.46
    POSITIVE LOGITS
     animations
    0.59
    绘画
    0.59
    Ligações
    0.59
     siamo
    0.57
     hlas
    0.57
    Makanan
    0.56
    创作
    0.55
    ні
    0.55
     bisog
    0.55
    শাক
    0.55
    Activations Density 0.001%

    No Known Activations