© 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. 115459
    Prev
    Next
    INDEX
    Explanations

    Marvel movies and specific names

    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
    kez
    -0.76
    琐
    -0.72
    pernicus
    -0.71
    tetten
    -0.70
     защиту
    -0.69
     årets
    -0.69
     dungeon
    -0.69
     liquor
    -0.69
     nocturnal
    -0.67
    В
    -0.67
    POSITIVE LOGITS
     MCU
    1.43
     Bucky
    1.35
    MCU
    1.12
     Avengers
    1.05
    mcu
    1.01
     Stark
    0.99
     Marvel
    0.95
     Hydra
    0.93
    Falcon
    0.93
     Soko
    0.93
    Activations Density 0.005%

    No Known Activations