© 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-262K
    7. 110528
    Prev
    Next
    INDEX
    Explanations

    prepare for

    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_262k_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
    トヨタ
    0.46
    නී
    0.45
    坯
    0.44
    şağı
    0.43
    
    0.43
    Fen
    0.42
    woord
    0.42
     stylistic
    0.42
    styling
    0.42
    ﾚ
    0.41
    POSITIVE LOGITS
    樣本
    0.48
    راً
    0.46
    probe
    0.43
    ਾਂ
    0.42
    eit
    0.41
    探测
    0.40
     probing
    0.39
    уре
    0.39
    ева
    0.39
     命令
    0.39
    Activations Density 0.001%

    No Known Activations