© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10841
    Prev
    Next
    INDEX
    Explanations

    supernatural creatures like vampires and wolves

    np_acts-logits-general · gemini-2.5-flash-lite

    supernatural transformations or forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Admiral
    0.49
     নৌ
    0.45
    賄
    0.45
     Admiral
    0.44
    宝
    0.41
    釣
    0.40
    intendo
    0.40
     চু
    0.39
     RNG
    0.39
     balloon
    0.39
    POSITIVE LOGITS
     vampire
    1.68
     vampires
    1.62
     vamp
    1.57
     Vamp
    1.51
     Vampire
    1.49
     werewolf
    1.29
    🧛
    1.07
     wolves
    1.02
     Dracula
    0.98
     Wolves
    0.93
    Activations Density 0.179%

    No Known Activations