© 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
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2031
    Prev
    Next
    INDEX
    Explanations

    favorite things

    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
    extent
    0.88
    舸
    0.84
     windings
    0.81
    状况
    0.80
     boundedness
    0.80
    anediyl
    0.80
    pertensive
    0.79
    metik
    0.79
     危
    0.79
    uerung
    0.78
    POSITIVE LOGITS
     favorite
    3.89
     favourite
    3.84
     favorites
    3.58
    favorite
    3.55
     Favorite
    3.47
     favourites
    3.34
     Favourite
    3.31
     FAVOR
    3.21
     fave
    3.21
     favorita
    3.20
    Activations Density 0.602%

    No Known Activations