© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81492
    Prev
    Next
    INDEX
    Explanations

    short duration

    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
    𝒔
    -0.85
     många
    -0.79
    észet
    -0.77
    गु
    -0.77
    floxacin
    -0.73
     więks
    -0.73
    逊
    -0.73
     nombreux
    -0.72
     Long
    -0.72
    此刻
    -0.71
    POSITIVE LOGITS
     short
    5.31
    short
    4.22
     brief
    3.75
    短
    3.70
    Short
    3.66
     коротки
    3.55
     kısa
    3.42
     kurze
    3.34
     Short
    3.31
    SHORT
    3.16
    Activations Density 0.097%

    No Known Activations