© 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. 12412
    Prev
    Next
    INDEX
    Explanations

    PyTorch tensors

    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
    mara
    1.24
    रान
    1.09
    red
    1.08
    সেন
    1.07
    amin
    1.04
    </i>
    1.03
    éd
    1.02
    oted
    1.01
    </em>
    0.99
    maz
    0.99
    POSITIVE LOGITS
    ,_
    1.52
     reh
    1.49
     meshes
    1.49
     isLoading
    1.49
     tc
    1.48
    悱
    1.46
     dpi
    1.42
    pute
    1.40
     veer
    1.40
     stupe
    1.40
    Activations Density 0.003%

    No Known Activations