© 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. 40-GEMMASCOPE-2-RES-65K
    7. 55289
    Prev
    Next
    INDEX
    Explanations

    description and conditions

    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_40_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
    けば
    0.39
     LCD
    0.37
     القاهرة
    0.37
    ledovatel
    0.35
     বিমানবন্দ
    0.35
    མ
    0.35
     नॉलेज
    0.35
     predecessor
    0.34
    每一
    0.34
    ,[
    0.33
    POSITIVE LOGITS
     повы
    0.45
     είναι
    0.44
    redu
    0.44
     reduces
    0.42
     decreases
    0.40
     reacts
    0.40
    looks
    0.40
     Фургал
    0.40
     looks
    0.39
     dries
    0.39
    Activations Density 0.012%

    No Known Activations