© 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-262K
    7. 49127
    Prev
    Next
    INDEX
    Explanations

    multilingual texts

    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_262k_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
    ла
    0.61
    ה
    0.59
    สเตอร์
    0.53
    0
    0.53
    FT
    0.52
     westbound
    0.52
    <h3>
    0.51
    人で
    0.51
    Ｕ
    0.50
    Android
    0.50
    POSITIVE LOGITS
     immobil
    0.62
     kund
    0.61
     yaad
    0.58
     immobili
    0.58
     infrastrukt
    0.57
     ఎలాంటి
    0.56
    üm
    0.56
     활동
    0.56
     kæ
    0.55
     نوش
    0.54
    Activations Density 0.000%

    No Known Activations