© 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. 45311
    Prev
    Next
    INDEX
    Explanations

    just tacked-on features

    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
    Ằ
    0.36
    loadImage
    0.35
     গণতন্ত্র
    0.35
    ഗ്
    0.34
     引
    0.34
     sneakers
    0.34
    项目
    0.34
    สั่ง
    0.33
    }^{(\
    0.33
    commun
    0.33
    POSITIVE LOGITS
     Medizin
    0.34
     pws
    0.34
     Rett
    0.34
     Medik
    0.34
     Op
    0.33
    tele
    0.33
     Riche
    0.32
     Medica
    0.32
    pyrrolo
    0.32
     Melton
    0.32
    Activations Density 0.003%

    No Known Activations