© 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
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1625
    Prev
    Next
    INDEX
    Explanations

    rich, future, markets, heavy load

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hoffnung
    0.69
     shadow
    0.66
    "
    0.61
     Killing
    0.60
     machine
    0.60
     Because
    0.60
     entrepreneurs
    0.59
     hat
    0.59
     because
    0.58
     hallucinations
    0.57
    POSITIVE LOGITS
                           
    1.11
                   
    1.04
                       
    1.04
                            
    1.03
                               
    1.03
                         
    1.02
                     
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.01
                              
    1.01
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.00
    Activations Density 0.608%

    No Known Activations