Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 291
    Prev
    Next
    INDEX
    Explanations

    phrases ending in ning

    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_16_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
    м
    0.55
    ं
    0.54
    ো
    0.54
    FERENCES
    0.54
    спубли
    0.53
    다
    0.52
    ރ
    0.52
     .”
    0.51
    на
    0.51
    و
    0.50
    POSITIVE LOGITS
     ਲ
    0.59
     stormwater
    0.53
     यात्री
    0.52
     ਪਰ
    0.52
     ਕੀਤਾ
    0.52
     व्हाउचर
    0.52
     limousine
    0.52
    henga
    0.51
     അയാൾ
    0.51
     tavern
    0.51
    Activations Density 0.000%

    No Known Activations