© 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. 4555
    Prev
    Next
    INDEX
    Explanations

    bladed tools and sharpening

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

    weapon or blade

    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
     transcriptome
    0.53
    нора
    0.49
    캘
    0.45
     transcripts
    0.44
    াজিক
    0.43
     Laundry
    0.42
     transcript
    0.41
    趸
    0.41
    頫
    0.40
    潢
    0.40
    POSITIVE LOGITS
     sword
    3.44
     swords
    3.20
     knife
    3.17
    刀
    3.17
     Sword
    2.98
     knives
    2.97
    Sword
    2.88
     dagger
    2.84
    knife
    2.81
    sword
    2.80
    Activations Density 0.182%

    No Known Activations