© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2297
    Prev
    Next
    INDEX
    Explanations

    ---

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     («
    1.16
    «
    1.09
    »
    1.08
     «
    1.04
     أيضًا
    1.00
    »,
    1.00
    »،
    1.00
    ًا
    1.00
    «,
    0.97
     \|
    0.96
    POSITIVE LOGITS
     .......
    4.72
     ........
    4.64
    ........
    4.63
    .......
    4.62
     ......
    4.48
    .........
    4.45
     ..........
    4.43
     .........
    4.43
    ……..
    4.40
    ..........
    4.38
    Activations Density 0.374%

    No Known Activations