© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    ```xml

    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
     keempat
    1.56
     cuarent
    1.42
     astonishment
    1.40
    ꗭ
    1.35
     mimpi
    1.35
     camadas
    1.34
     diámetro
    1.33
    TrackedDevice
    1.33
     tedavi
    1.31
     birkaç
    1.30
    POSITIVE LOGITS
     My
    1.20
    My
    1.02
     Also
    1.02
    2
    0.98
     Torch
    0.97
     ณ
    0.89
    also
    0.88
    1
    0.88
    ข่าว
    0.88
    \
    0.88
    Activations Density 0.007%

    No Known Activations