© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15644
    Prev
    Next
    INDEX
    Explanations

    street names and directions

    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
    د
    0.47
    Id
    0.46
     tembok
    0.45
    Clear
    0.44
     Anmeldung
    0.43
     Setiap
    0.43
     सचिवालय
    0.43
    Wir
    0.41
     Areas
    0.40
    چ
    0.40
    POSITIVE LOGITS
    上的
    0.50
    系の
    0.45
    一顆
    0.45
     ধারে
    0.45
     medallions
    0.43
    ᕋ
    0.42
    梸
    0.42
     toàn
    0.42
     revêt
    0.41
     perspiciatis
    0.41
    Activations Density 0.021%

    No Known Activations