© 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. 1259
    Prev
    Next
    INDEX
    Explanations

    a nod to

    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
     donut
    1.49
     doughnut
    1.47
    ங்காய்
    1.46
     tiki
    1.46
     boxShadow
    1.45
     자동차
    1.44
     탄
    1.42
     (%
    1.42
     블루
    1.39
     borderRadius
    1.38
    POSITIVE LOGITS
    ivam
    1.42
    wyd
    1.36
    ía
    1.23
    ため
    1.22
    as
    1.16
    लम
    1.15
    arán
    1.15
     Zudem
    1.14
    ivité
    1.13
     isso
    1.13
    Activations Density 0.240%

    No Known Activations