© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14929
    Prev
    Next
    INDEX
    Explanations

    antioxidants

    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
    𝐡
    1.59
     Jun
    1.58
     Pin
    1.57
     Bin
    1.57
     gan
    1.55
     t
    1.51
    :[/
    1.51
     Jan
    1.49
    ല്
    1.49
     sfr
    1.48
    POSITIVE LOGITS
    рец
    1.91
    )':
    1.88
    ißler
    1.86
    affaires
    1.84
    OMO
    1.80
    ই
    1.80
    ulu
    1.77
    ฤษ
    1.77
    dés
    1.77
    ்துறை
    1.76
    Activations Density 0.052%

    No Known Activations