© 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. 650
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions and adverbs

    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
     లేదా
    1.08
    এবং
    1.05
     మరియు
    1.03
    인데요
    1.00
     மற்றும்
    0.99
     ಅಥವಾ
    0.94
     અથવા
    0.93
    或
    0.93
     अथवा
    0.93
    หรือ
    0.93
    POSITIVE LOGITS
     fortunately
    2.15
     luckily
    2.11
     alas
    2.08
     thankfully
    2.08
     frankly
    1.98
     sadly
    1.91
     unfortunately
    1.91
     admittedly
    1.88
     since
    1.87
     interestingly
    1.87
    Activations Density 1.526%

    No Known Activations