© 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. 2180
    Prev
    Next
    INDEX
    Explanations

    exam questions

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

    Instacart

    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
    ﮅ
    0.40
    писи
    0.40
     lactation
    0.40
    ategy
    0.39
    rative
    0.39
     nurture
    0.39
    世纪
    0.39
    狧
    0.38
    耻
    0.38
    шым
    0.38
    POSITIVE LOGITS
     Tier
    0.42
     Borden
    0.42
    <0x9B>
    0.42
     vampire
    0.38
     लसी
    0.38
     Adapter
    0.37
    Tier
    0.37
     Vampire
    0.37
    ibacter
    0.36
     ሂ
    0.36
    Activations Density 0.000%

    No Known Activations