© 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. 31-GEMMASCOPE-2-RES-65K
    7. 15002
    Prev
    Next
    INDEX
    Explanations

    policy created

    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
     ب
    0.45
    ULAR
    0.43
     wieder
    0.42
     আস্তে
    0.41
    回目の
    0.41
    R
    0.41
     tekrar
    0.40
    س
    0.40
    flow
    0.40
     ل
    0.40
    POSITIVE LOGITS
     váy
    0.43
     apostila
    0.43
     INVALID
    0.42
    并非
    0.41
     οικονομ
    0.39
     Pendidikan
    0.39
     альбо
    0.39
     शारीरिक
    0.38
     działal
    0.38
     CATEG
    0.37
    Activations Density 0.040%

    No Known Activations