© 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. 55260
    Prev
    Next
    INDEX
    Explanations

    Springer Science publications

    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
     봄
    0.46
    Spring
    0.46
    春
    0.45
    봄
    0.45
    Sprites
    0.45
     春
    0.44
    SPRING
    0.43
     springs
    0.43
     spring
    0.42
     SPRING
    0.42
    POSITIVE LOGITS
     Science
    0.46
    㩴
    0.40
     سائٹ
    0.38
     क्लास
    0.37
     ٹیکسٹ
    0.37
     Compressed
    0.37
     Level
    0.35
     science
    0.35
    ienste
    0.35
     गोर
    0.35
    Activations Density 0.002%

    No Known Activations