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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 609
    Prev
    Next
    INDEX
    Explanations

    categories further

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    <sub>
    0.89
     거야
    0.83
    <sup>
    0.82
    用い
    0.80
      
    0.80
    致力
    0.80
     prestasi
    0.78
    あるいは
    0.76
    んですよ
    0.76
    近日
    0.76
    POSITIVE LOGITS
     disappointed
    1.29
    
    1.19
     disappointing
    1.18
     hubby
    1.18
    😑
    1.17
     snd
    1.15
    🫤
    1.15
    😫
    1.14
    😡
    1.12
     disappointment
    1.12
    Activations Density 0.811%

    No Known Activations