© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings 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_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
    /
    1.68
    ،
    1.66
    -
    1.64
    .
    1.58
    '
    1.49
    
    1.44
    )،
    1.44
    ,
    1.44
    cut
    1.43
    ung
    1.42
    POSITIVE LOGITS
     우리는
    2.15
     we
    2.13
     jeśli
    2.08
     they
    2.04
     이는
    1.99
     koska
    1.96
     kuten
    1.92
     çünkü
    1.89
     it
    1.87
     उन्होंने
    1.85
    Activations Density 1.361%

    No Known Activations