© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2851
    Prev
    Next
    INDEX
    Explanations

    as possible

    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_17_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
     Akan
    0.64
     warto
    0.64
                      
    0.63
     тема
    0.62
    Fam
    0.62
                    
    0.61
                        
    0.60
                     
    0.60
    ---------------+
    0.60
     若
    0.59
    POSITIVE LOGITS
     possible
    2.91
    possible
    2.49
     posible
    2.45
     Possible
    2.40
     possibile
    2.39
     possível
    2.35
    Possible
    2.00
     POSSIBLE
    1.96
     possibili
    1.95
     возможных
    1.95
    Activations Density 0.183%

    No Known Activations