© 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. 53-GEMMASCOPE-2-RES-65K
    7. 7096
    Prev
    Next
    INDEX
    Explanations

    ways in

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

    cookie followed by quote

    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
    ρυθ
    0.39
     scraps
    0.38
    प्रिल
    0.37
    棠
    0.37
    ቢያ
    0.36
    влено
    0.35
    gson
    0.35
     bystanders
    0.35
    법
    0.34
    форма
    0.34
    POSITIVE LOGITS
    末
    0.42
    astype
    0.37
    ::_
    0.36
     Laid
    0.36
     नपु
    0.36
     Awakening
    0.36
     Smiling
    0.35
    ద్దా
    0.35
     रू
    0.35
     sello
    0.35
    Activations Density 0.013%

    No Known Activations