© 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. 50199
    Prev
    Next
    INDEX
    Explanations

    watercolor effect

    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
    methylsulfanyl
    0.44
     ヒ
    0.44
     cartil
    0.44
     pona
    0.44
    ̷
    0.44
     பாபிலோ
    0.43
     ถึง
    0.43
     sklad
    0.43
     baseApiPath
    0.42
     dike
    0.42
    POSITIVE LOGITS
    ক
    0.46
    ب
    0.44
     fusing
    0.44
    น
    0.43
     gratu
    0.43
     financement
    0.43
     reproduces
    0.42
    <0xA8>
    0.41
     Issue
    0.41
     reproducing
    0.41
    Activations Density 0.008%

    No Known Activations