© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4224
    Prev
    Next
    INDEX
    Explanations

    start of sentences after punctuation

    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_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
    Connor
    1.63
     Enoch
    1.45
    effer
    1.38
     Toot
    1.37
     Carpent
    1.37
    Josh
    1.37
    Helen
    1.34
    İ
    1.33
    ቱም
    1.33
    Hector
    1.33
    POSITIVE LOGITS
    ↵
    1.12
     sensible
    1.04
     rifi
    1.03
    행
    0.99
     mang
    0.99
    mang
    0.96
     adentro
    0.96
    nellement
    0.93
     fiss
    0.91
     significative
    0.91
    Activations Density 0.101%

    No Known Activations