© 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. 3320
    Prev
    Next
    INDEX
    Explanations

    experience, background, intend

    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
    trunc
    0.50
    ي
    0.47
    i
    0.47
    ட்டின்
    0.46
    κης
    0.45
    deriv
    0.45
    ाग्राम
    0.44
    に関
    0.43
    ಕಾಶ
    0.43
    гий
    0.43
    POSITIVE LOGITS
     занятия
    0.49
     -
    0.49
     to
    0.46
     است
    0.46
     pada
    0.45
     মারাত্মক
    0.45
    перь
    0.45
     raspberry
    0.44
     yang
    0.44
     vous
    0.44
    Activations Density 0.000%

    No Known Activations