© 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. 2838
    Prev
    Next
    INDEX
    Explanations

    need and want

    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
     etc
    1.92
     इत्यादि
    1.65
    等の
    1.64
     dll
    1.63
    等
    1.58
    等が
    1.57
    etc
    1.55
     usw
    1.53
     Etc
    1.52
     및
    1.45
    POSITIVE LOGITS
     unsurprisingly
    1.77
     decidedly
    1.75
     strikingly
    1.73
     spectacularly
    1.68
     conund
    1.67
     gleaming
    1.63
     upheaval
    1.59
     windfall
    1.55
     glittering
    1.52
     burgeoning
    1.51
    Activations Density 2.316%

    No Known Activations