© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 342
    Prev
    Next
    INDEX
    Explanations

    professions and their specialties

    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_13_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
    ்சை
    1.12
    டுகிறது
    1.07
     WIDTH
    1.06
    它們
    1.02
    ו
    1.02
    ிருந்தது
    1.01
    ள்ளது
    1.00
    ವು
    0.97
    它
    0.96
    
    0.96
    POSITIVE LOGITS
     who
    1.46
    who
    1.26
     whom
    1.19
     emeritus
    1.18
     extraordinaire
    1.11
    whom
    1.05
     whose
    1.02
    innen
    0.99
     whos
    0.97
     Emeritus
    0.97
    Activations Density 1.288%

    No Known Activations