© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76767
    Prev
    Next
    INDEX
    Explanations

    Teen Wolf television series

    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
    ל
    -0.80
    Crown
    -0.72
     Crown
    -0.70
     Ig
    -0.69
     ویتامین
    -0.68
     forts
    -0.65
     flats
    -0.64
    ?!
    -0.64
     Elon
    -0.64
    Illustration
    -0.63
    POSITIVE LOGITS
     Stiles
    1.31
     Beacon
    1.07
     werewolf
    1.03
    Argent
    0.93
     lacrosse
    0.91
     wolf
    0.88
     Hale
    0.88
    Stit
    0.87
    Beacon
    0.85
     Stil
    0.83
    Activations Density 0.016%

    No Known Activations