© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1560
    Prev
    Next
    INDEX
    Explanations

    punctuation and the word Bring

    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_13_width_65k_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
    agun
    1.07
    renched
    1.05
    olymer
    1.05
    pyrrol
    1.02
    ially
    1.01
    ategy
    1.01
    inyl
    1.01
    ë
    1.00
    ukkh
    0.98
    induced
    0.98
    POSITIVE LOGITS
     Excelente
    2.00
     Also
    1.96
     我
    1.91
     Sorry
    1.86
     然后
    1.86
     所以
    1.85
     vamos
    1.85
     बहुत
    1.84
     Hopefully
    1.84
     本当
    1.84
    Activations Density 1.347%

    No Known Activations