© 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. 54775
    Prev
    Next
    INDEX
    Explanations

    windshields, wipers, glass

    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
     ಅಲ
    0.42
    𝕀
    0.41
    MovementControls
    0.40
    部屋
    0.38
    しましょう
    0.38
    𝔼
    0.38
    房间
    0.37
    пень
    0.37
    Rig
    0.37
    𝙿
    0.37
    POSITIVE LOGITS
     windshield
    1.41
     windscreen
    1.20
     wiper
    1.09
     wipers
    1.08
     kaca
    0.77
     glass
    0.65
     kính
    0.64
     glasses
    0.63
     visor
    0.63
     стекла
    0.63
    Activations Density 0.028%

    No Known Activations