© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14619
    Prev
    Next
    INDEX
    Explanations

    AI limitations and purpose

    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_7_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
    ujemy
    1.85
    ული
    1.72
     \&
    1.68
     लगी
    1.57
    sein
    1.56
    edom
    1.53
     people
    1.52
     Nei
    1.51
    sez
    1.50
    龵
    1.48
    POSITIVE LOGITS
     posh
    2.31
     nemesis
    2.29
     glam
    2.27
     glamour
    2.17
     shenanigans
    2.16
     blissful
    2.15
     veritable
    2.13
     истины
    2.13
     vanqu
    2.12
     divina
    2.12
    Activations Density 0.588%

    No Known Activations