© 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. 67026
    Prev
    Next
    INDEX
    Explanations

    military, official, or specific roles

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

    business or technical context

    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
    م
    0.59
    و
    0.51
     Benoit
    0.42
    Classpath
    0.41
     packing
    0.41
     hopeless
    0.41
    Packing
    0.39
     pack
    0.39
     Mal
    0.39
    ו
    0.39
    POSITIVE LOGITS
     стрельца
    0.51
     камен
    0.50
     RADIATION
    0.49
     AGRICULTURAL
    0.46
    İZ
    0.45
     solitons
    0.45
    üz
    0.45
    şı
    0.45
     стрелецкой
    0.44
    দর্শনে
    0.44
    Activations Density 0.001%

    No Known Activations