© 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. 6559
    Prev
    Next
    INDEX
    Explanations

    categorized broken

    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
    𝐢
    2.08
    𝑟
    1.99
    iendo
    1.90
    𝐫
    1.89
    Civil
    1.79
     ‘‘
    1.78
    𝐭
    1.76
    Wa
    1.73
    통령
    1.73
     खरा
    1.73
    POSITIVE LOGITS
    ไง
    1.95
    胺
    1.90
    ówczas
    1.86
    icularis
    1.82
     orderly
    1.79
    chaos
    1.75
     hypothalam
    1.75
     warp
    1.69
    plotting
    1.69
     somew
    1.67
    Activations Density 0.437%

    No Known Activations