© 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. 103469
    Prev
    Next
    INDEX
    Explanations

    case in point

    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
    櫈
    -1.02
    важа
    -0.95
    träglich
    -0.91
    损伤
    -0.91
     bezw
    -0.90
     Strukt
    -0.90
    samt
    -0.89
    BasePath
    -0.89
     myös
    -0.88
    ALLEN
    -0.88
    POSITIVE LOGITS
     case
    5.13
    Case
    4.09
     Case
    4.03
     example
    3.66
    case
    3.66
     cases
    2.86
    Example
    2.83
     Example
    2.77
    example
    2.73
     CASE
    2.69
    Activations Density 0.070%

    No Known Activations