© 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. 98339
    Prev
    Next
    INDEX
    Explanations

    film titles and artistic works

    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
     hypocrisy
    -0.75
     asked
    -0.74
     ہم
    -0.73
     Aoki
    -0.72
     derived
    -0.71
     圖
    -0.71
    fontStyle
    -0.69
    安倍
    -0.68
    onded
    -0.68
     fondi
    -0.67
    POSITIVE LOGITS
     Dune
    0.94
    coda
    0.88
    Dune
    0.88
    Lic
    0.83
     Macbeth
    0.82
     COD
    0.79
     dune
    0.77
     مح
    0.77
    Scala
    0.77
     licor
    0.77
    Activations Density 0.019%

    No Known Activations