© 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. 30836
    Prev
    Next
    INDEX
    Explanations

    parts or locations

    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
     आएंगी
    0.50
    व
    0.48
     aptly
    0.48
    slategray
    0.46
    𝘢
    0.46
    が生
    0.44
    𒀊
    0.44
    મ
    0.44
     प्रॉब्ल
    0.43
    ஆ
    0.43
    POSITIVE LOGITS
     POC
    0.45
     U
    0.45
     Jansen
    0.44
     एस
    0.43
     S
    0.43
     Po
    0.42
     qualidade
    0.42
    engaged
    0.41
     D
    0.41
     PPC
    0.41
    Activations Density 0.001%

    No Known Activations