© 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. 63322
    Prev
    Next
    INDEX
    Explanations

    Left Right traversal

    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
    стоян
    0.40
    ipient
    0.40
     steady
    0.39
    ↯
    0.39
     ongoing
    0.39
     broader
    0.39
     cohesive
    0.39
     immutable
    0.39
     প্যাকে
    0.38
     brav
    0.38
    POSITIVE LOGITS
     gobiernos
    0.46
     亻
    0.46
    शियों
    0.45
    𝓃
    0.45
    咚
    0.44
     Obstetrics
    0.43
     RIGHT
    0.43
     Frankfort
    0.43
     FARM
    0.42
    öm
    0.42
    Activations Density 0.004%

    No Known Activations