© 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-16K
    7. 8632
    Prev
    Next
    INDEX
    Explanations

    scientific notation with units

    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
     ataupun
    1.58
    もしくは
    1.56
    或
    1.53
     atau
    1.52
    或是
    1.51
     oder
    1.50
    とか
    1.46
     hoặc
    1.44
    や
    1.44
     actuales
    1.44
    POSITIVE LOGITS
     converging
    1.02
     send
    0.98
     valence
    0.98
    ilg
    0.97
     interconnected
    0.95
    Tl
    0.93
    lg
    0.93
    trk
    0.92
    valence
    0.91
     denote
    0.91
    Activations Density 0.015%

    No Known Activations