© 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. 5501
    Prev
    Next
    INDEX
    Explanations

    sea + common words

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

    sea and related marine life/phenomena

    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
    Влади
    0.40
     Diagnose
    0.40
    ති
    0.38
    徕
    0.37
    ักษณะ
    0.37
    Advisor
    0.37
    هيل
    0.37
    訫
    0.37
    ếu
    0.36
     मुखिया
    0.36
    POSITIVE LOGITS
    weed
    0.75
     urch
    0.66
     sea
    0.64
     breeze
    0.60
     Sea
    0.59
     creatures
    0.59
     breezes
    0.59
    Sea
    0.58
     cucumber
    0.58
     cucumbers
    0.58
    Activations Density 0.033%

    No Known Activations