© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 15229
    Prev
    Next
    INDEX
    Explanations

    words and vocabulary

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

    dictionary words

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

    words

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    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
    حديد
    0.61
    ๊
    0.59
     decompression
    0.55
     shoving
    0.55
     bracing
    0.54
     optimizing
    0.53
    規劃
    0.53
     rotational
    0.52
    離島
    0.52
     prepping
    0.51
    POSITIVE LOGITS
     शब्द
    0.98
     શબ્
    0.97
     Words
    0.95
     слово
    0.88
    词
    0.87
     words
    0.86
    lexeme
    0.86
     palabras
    0.84
     söz
    0.83
     Wörter
    0.82
    Activations Density 0.158%

    No Known Activations