© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5520
    Prev
    Next
    INDEX
    Explanations

    copiar questions

    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
     
    0.79
    मध्यप्रदेश
    0.74
     altercation
    0.72
     bylaws
    0.72
     voire
    0.71
     ૧
    0.69
    cie
    0.68
    女
    0.68
     solicitor
    0.68
     Esq
    0.67
    POSITIVE LOGITS
     Obwohl
    0.93
    <unused536>
    0.79
     Zhen
    0.77
     QuantityOnHand
    0.76
    いくつかの
    0.75
     χρησιμοποι
    0.74
     Einige
    0.72
     มัน
    0.71
     overfitting
    0.71
     উত্প
    0.71
    Activations Density 0.059%

    No Known Activations