© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10697
    Prev
    Next
    INDEX
    Explanations

    questions about context and examples

    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
     If
    1.06
     because
    1.04
     There
    1.00
     нельзя
    0.99
     I
    0.98
     O
    0.97
     porque
    0.96
     О
    0.96
     PCR
    0.96
     нет
    0.95
    POSITIVE LOGITS
     evocative
    1.49
     meditative
    1.38
     fascinated
    1.37
     captivated
    1.37
    geoType
    1.36
     imbued
    1.35
     evoc
    1.32
    inspir
    1.31
     evoking
    1.31
    expressing
    1.28
    Activations Density 0.114%

    No Known Activations