© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    in short phrases or summaries

    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
    acao
    1.34
     ?
    1.19
     cs
    1.16
     tit
    1.15
     z
    1.13
     Ci
    1.11
     sl
    1.09
     Gu
    1.09
    ACAO
    1.09
     É
    1.05
    POSITIVE LOGITS
    ്യ
    1.62
    ้
    1.54
     nefarious
    1.53
    っ
    1.50
     impetus
    1.48
    ̵
    1.48
     burdensome
    1.48
     insidious
    1.48
     মূর্তি
    1.47
     bequeathed
    1.46
    Activations Density 0.183%

    No Known Activations