© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1892
    Prev
    Next
    INDEX
    Explanations

    light bends, reflection, switches

    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
    sker
    3.01
    attet
    2.74
    स्मै
    2.66
    ymoon
    2.66
     deg
    2.59
    iesen
    2.54
    𝐨
    2.53
     primarySwatch
    2.52
    ategy
    2.49
    inkan
    2.47
    POSITIVE LOGITS
    al
    3.11
    ার
    2.57
     egress
    2.26
    ிற்ப
    2.23
    BIC
    2.16
    া
    2.15
    ங்குகள்
    2.14
     tra
    2.14
    ಾರದ
    2.12
    east
    2.11
    Activations Density 0.408%

    No Known Activations