© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11083
    Prev
    Next
    INDEX
    Explanations

    non-english words and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    다
    1.18
    ה
    1.13
    ੀ
    1.13
    т
    1.07
    م
    1.05
    e
    1.05
    aient
    1.02
    a
    1.02
    ف
    0.99
    ক
    0.98
    POSITIVE LOGITS
    ificaciones
    0.93
    ग्विजय
    0.92
    ညီ
    0.90
    ంట్
    0.86
     synagogues
    0.84
     Vér
    0.83
    ப்படவில்லை
    0.82
    ;?>
    0.82
    द्धाल
    0.81
     গিয়েছিল
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.