© 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. 29622
    Prev
    Next
    INDEX
    Explanations

    Asakusa

    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
     ounces
    0.45
    ्यारह
    0.45
     packages
    0.42
    +,
    0.42
    烟
    0.41
    Windows
    0.40
     proporcion
    0.40
     rapides
    0.40
     дзяржа
    0.40
    𝚅
    0.40
    POSITIVE LOGITS
    atthakath
    0.44
    etzten
    0.44
     ketemu
    0.42
    hamed
    0.41
    hei
    0.41
    hanti
    0.41
    hā
    0.41
    imsu
    0.41
     హీ
    0.40
     উত্তম
    0.40
    Activations Density 0.010%

    No Known Activations