© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 110528
    Prev
    Next
    INDEX
    Explanations

    subject matter

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    坯
    0.48
    şağı
    0.47
    トヨタ
    0.46
    
    0.44
    FEN
    0.43
    Fen
    0.43
    WR
    0.42
    ឪ
    0.42
    Put
    0.41
    भारतीय
    0.41
    POSITIVE LOGITS
    راً
    0.52
    樣本
    0.46
    ਾਂ
    0.41
    eit
    0.41
     meromorphic
    0.39
    ڈیو
    0.39
    探测
    0.39
     الهول
    0.38
    ائش
    0.38
    probe
    0.38
    Activations Density 0.002%

    No Known Activations