© 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. 5984
    Prev
    Next
    INDEX
    Explanations

    988 crisis line

    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
     already
    1.07
     ever
    0.96
    疹
    0.94
     interchangeably
    0.90
     +
    0.89
    娟
    0.88
     rightly
    0.87
     ditches
    0.87
    +
    0.87
     shippers
    0.86
    POSITIVE LOGITS
    Baş
    1.23
    Berat
    1.23
    Accessibility
    1.19
    िकुलर
    1.17
    قب
    1.17
    ποίηση
    1.16
    ᒐ
    1.15
    Peak
    1.15
    Calibration
    1.14
     Размер
    1.13
    Activations Density 0.030%

    No Known Activations