© 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. 31285
    Prev
    Next
    INDEX
    Explanations

    section headers and keywords

    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
    简单
    0.46
    Street
    0.45
    庞
    0.45
    Simple
    0.43
    是一种
    0.42
    扑
    0.41
    Situation
    0.41
     basit
    0.41
    多的
    0.40
    X
    0.40
    POSITIVE LOGITS
    vykor
    0.48
     Nhân
    0.46
    ματος
    0.45
     اللہ
    0.44
    או
    0.44
    llvm
    0.42
     পেয়েছিলাম
    0.42
     שלו
    0.42
     ऋण
    0.42
     cu
    0.42
    Activations Density 0.010%

    No Known Activations