© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8415
    Prev
    Next
    INDEX
    Explanations

    buy essay

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

    explaining things and concepts

    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_53_width_65k_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
    ད
    0.27
     በፍ
    0.27
     kembali
    0.26
    க்குக
    0.26
    死去
    0.25
     spust
    0.25
    ণাস্ত্র
    0.25
     kamen
    0.25
    󠁬
    0.25
     masukkan
    0.25
    POSITIVE LOGITS
     critiques
    0.29
    kla
    0.26
     fax
    0.26
    首席
    0.25
     Tez
    0.25
     foundational
    0.25
     SWOT
    0.25
     Notably
    0.25
     payday
    0.25
     tackled
    0.25
    Activations Density 0.181%

    No Known Activations