© 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. 2206
    Prev
    Next
    INDEX
    Explanations

    natural phenomena

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

    natural language, occurring, sources

    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
    ದಲ
    0.44
     natuurlijk
    0.44
    динку
    0.44
    秆
    0.41
     natürlich
    0.41
    egd
    0.41
     naturalmente
    0.40
    맟
    0.39
    Укупно
    0.39
     grunds
    0.38
    POSITIVE LOGITS
    istic
    1.02
     occurring
    1.00
     occuring
    0.93
    occurring
    0.90
     disasters
    0.88
    istically
    0.88
     disaster
    0.76
     phenomena
    0.75
    ISTIC
    0.73
    災害
    0.69
    Activations Density 0.056%

    No Known Activations