© 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. 116778
    Prev
    Next
    INDEX
    Explanations

    Lady Gaga, Honolulu, Hawaii

    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
    Decent
    -0.74
    LiveData
    -0.73
    gorithm
    -0.73
     achieving
    -0.69
    arshan
    -0.68
     Bay
    -0.67
     decent
    -0.66
     However
    -0.66
     dehydration
    -0.65
     accurate
    -0.65
    POSITIVE LOGITS
     smaak
    0.84
    endant
    0.79
    illir
    0.77
    ogyn
    0.77
     AGC
    0.77
    iatric
    0.76
     Honolulu
    0.75
     Cope
    0.75
     chang
    0.75
     CHANG
    0.75
    Activations Density 0.057%

    No Known Activations