© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10130
    Prev
    Next
    INDEX
    Explanations

    generate flight or flying

    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_31_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
     കോടതി
    0.49
     मसा
    0.46
    浒
    0.45
     shui
    0.44
    銭
    0.43
     आगा
    0.43
    🥒
    0.42
    汕
    0.42
    знача
    0.41
     रिप्रोड
    0.41
    POSITIVE LOGITS
    飛行
    1.43
    飞行
    1.34
     flying
    1.28
     flight
    1.19
    flying
    1.17
     aeronaut
    1.13
     Flight
    1.11
     Flying
    1.10
     airfoil
    1.09
     wings
    1.08
    Activations Density 0.142%

    No Known Activations