© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6136
    Prev
    Next
    INDEX
    Explanations

    was already sketching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     members
    0.99
    aic
    0.84
    members
    0.83
    っいて
    0.82
     underdeveloped
    0.82
    殖
    0.82
     évek
    0.82
    膿
    0.81
    athom
    0.79
    発展
    0.79
    POSITIVE LOGITS
     quien
    2.28
     Maß
    2.22
     acompañado
    2.21
     acompañada
    2.17
     그의
    2.13
     ersetzt
    2.09
     كتابه
    2.09
     exacting
    2.04
     responsável
    2.03
    駕駛
    1.98
    Activations Density 0.150%

    No Known Activations