© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58958
    Prev
    Next
    INDEX
    Explanations

    Swift and Objective-C code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oniec
    -0.91
    mbic
    -0.88
     dispoz
    -0.85
     embo
    -0.85
     Sf
    -0.83
    キーボード
    -0.82
     passiert
    -0.81
     conic
    -0.81
     Caterina
    -0.81
    umman
    -0.81
    POSITIVE LOGITS
    BitConverter
    1.00
     distance
    0.84
     should
    0.83
     aDecoder
    0.79
    northeast
    0.77
    藁
    0.76
    NSUInteger
    0.76
     Entstehung
    0.76
    /).
    0.75
    umblr
    0.75
    Activations Density 0.034%

    No Known Activations