© 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. 48036
    Prev
    Next
    INDEX
    Explanations

    Fifty Shades; numbers

    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
     huiles
    -1.05
     İç
    -0.90
     impré
    -0.88
     уди
    -0.83
     Atlantis
    -0.83
     spawn
    -0.82
    spawn
    -0.81
     médec
    -0.80
     Modus
    -0.80
     Eduardo
    -0.79
    POSITIVE LOGITS
     reasons
    0.99
     Before
    0.94
     things
    0.93
     for
    0.90
     not
    0.88
    +
    0.85
     ways
    0.84
    Before
    0.83
     Things
    0.83
     Reasons
    0.80
    Activations Density 0.040%

    No Known Activations