© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 122568
    Prev
    Next
    INDEX
    Explanations

    Trojan horse

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

    clones, automatic income, crimes, listings

    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_31_width_262k_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
     hyperplasia
    0.47
    VL
    0.43
    ;
    0.41
    uleiro
    0.40
    QP
    0.40
     chamar
    0.40
    RI
    0.40
    VP
    0.39
    Ñ
    0.39
     વ
    0.39
    POSITIVE LOGITS
     Inglis
    0.48
     Cordova
    0.47
     termes
    0.46
     Pow
    0.46
    𝑘
    0.45
     Staats
    0.45
     Oficial
    0.45
     espirit
    0.44
    努
    0.44
     Kriegs
    0.44
    Activations Density 0.001%

    No Known Activations