© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    is followed by likely or growing

    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_17_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
    <unused1324>
    1.99
    <unused1592>
    1.98
     ihū
    1.98
    𒂦
    1.97
    􀍷
    1.97
    𒁈
    1.97
    𒇭
    1.97
     Iccevam
    1.97
    𒈣
    1.96
    niOkno
    1.96
    POSITIVE LOGITS
    ...
    1.17
      
    1.13
    …
    1.08
    ↵
    1.01
    ↵↵
    0.99
                                   
    0.97
        
    0.92
    <b>
    0.90
    ....
    0.89
       
    0.89
    Activations Density 1.384%

    No Known Activations