© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14270
    Prev
    Next
    INDEX
    Explanations

    handling exceptions with 'e'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    മെ
    1.34
    मस
    1.31
     एडिटिंग
    1.27
    ฏ
    1.27
    ewarm
    1.27
     breathing
    1.27
    addling
    1.27
     قوات
    1.26
    诰
    1.25
    Má
    1.25
    POSITIVE LOGITS
     defra
    1.61
     fraudsters
    1.57
     Coxeter
    1.57
     brokerage
    1.48
     Realtor
    1.47
     Realtors
    1.47
     securities
    1.44
     Pawn
    1.44
     scammers
    1.44
     burglary
    1.43
    Activations Density 0.391%

    No Known Activations