© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48464
    Prev
    Next
    INDEX
    Explanations

    assassin and Creed

    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
    备案
    -0.75
    ֮
    -0.72
     onco
    -0.71
    ってみて
    -0.70
    Cycling
    -0.70
     adven
    -0.69
     diaspora
    -0.68
    もあって
    -0.68
    ！！！！！
    -0.68
    ươ
    -0.68
    POSITIVE LOGITS
     Assassin
    1.48
    Assassin
    1.39
     brotherhood
    1.21
     assassin
    1.20
     Creed
    1.19
     Brotherhood
    1.16
     Ass
    1.13
     Alta
    1.09
    assassin
    1.06
     Anim
    1.05
    Activations Density 0.016%

    No Known Activations