© 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. 1341
    Prev
    Next
    INDEX
    Explanations

    fatty core

    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
    Cet
    1.88
    bage
    1.84
    तावनी
    1.76
     Über
    1.71
     때
    1.55
    ্ত
    1.55
    ্তির
    1.54
     appuy
    1.52
    ção
    1.49
    ক্ষে
    1.48
    POSITIVE LOGITS
    lengths
    2.60
     lengths
    2.56
     wheelbase
    2.54
     trajets
    2.42
    逖
    2.39
    ्स
    2.39
    eness
    2.36
    𝑠
    2.36
    length
    2.36
    sf
    2.35
    Activations Density 0.715%

    No Known Activations