© 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. 174083
    Prev
    Next
    INDEX
    Explanations

    military and officials in multiple languages

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

    do not attempt to engage

    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
    );*/
    0.44
    fhir
    0.43
    buscador
    0.43
    ाल
    0.42
    ENCE
    0.42
    기로
    0.42
    emitter
    0.42
    球面
    0.42
     optimum
    0.42
    allele
    0.42
    POSITIVE LOGITS
    军事
    0.54
     funcionários
    0.52
     stronę
    0.48
    聃
    0.48
     नवंबर
    0.47
     militares
    0.47
     funcionarios
    0.47
     अधिकारी
    0.46
    鲸
    0.46
     अधिकारियों
    0.46
    Activations Density 0.000%

    No Known Activations