© 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. 89
    Prev
    Next
    INDEX
    Explanations

    U.S., Dermoscopy, Bruttoinlandsprodukt, Slightly

    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
     and
    1.07
     a
    1.05
    1
    0.97
    2
    0.97
    3
    0.96
     to
    0.94
    0
    0.93
    4
    0.91
    9
    0.89
     been
    0.88
    POSITIVE LOGITS
    Przyp
    1.76
    𒌍
    1.72
    𒊑
    1.69
    Kiza
    1.69
    REGIUNE
    1.68
     Pusenkoff
    1.68
    𒀝
    1.67
    𒁍
    1.67
    ꔰ
    1.67
     związku
    1.66
    Activations Density 0.089%

    No Known Activations