© 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. 15659
    Prev
    Next
    INDEX
    Explanations

    like a

    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
     действительно
    0.85
     tred
    0.81
     davvero
    0.78
     ö
    0.77
     మేరకు
    0.75
     oznac
    0.75
     যথাযথ
    0.75
     prop
    0.74
     gioc
    0.73
    尺
    0.73
    POSITIVE LOGITS
    ]="
    0.95
    backers
    0.93
    shirt
    0.92
    Shen
    0.92
    arynx
    0.91
    aport
    0.90
    shen
    0.90
    hyp
    0.88
    achine
    0.87
     Shirt
    0.86
    Activations Density 0.151%

    No Known Activations