© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10729
    Prev
    Next
    INDEX
    Explanations

    weight gain or loss

    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_22_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
    ടന
    1.00
    duire
    0.91
    드로
    0.90
     khe
    0.89
    ळी
    0.88
     اع
    0.88
    フグ
    0.87
    섬
    0.86
     waveguides
    0.85
    等着
    0.84
    POSITIVE LOGITS
     gain
    1.73
     Gain
    1.62
    loss
    1.61
     loss
    1.54
    gain
    1.49
    lifting
    1.42
     Loss
    1.40
    Gain
    1.38
    Loss
    1.34
     LOSS
    1.28
    Activations Density 0.038%

    No Known Activations