© 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. 84159
    Prev
    Next
    INDEX
    Explanations

    attended, went, graduated

    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
    ceo
    -0.85
     tratti
    -0.81
    ẹn
    -0.77
    向
    -0.76
     Quake
    -0.75
    TypeEnum
    -0.71
     Subpart
    -0.71
    ピア
    -0.71
    istin
    -0.70
    正在
    -0.69
    POSITIVE LOGITS
     attended
    3.69
     went
    2.97
     graduated
    2.88
    attended
    2.52
     attend
    2.47
     attending
    2.25
    Went
    2.22
    went
    2.06
    Atten
    2.06
     graduating
    1.92
    Activations Density 0.066%

    No Known Activations