© 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. 12797
    Prev
    Next
    INDEX
    Explanations

    mental illness

    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
     erz
    1.25
    、「
    1.24
    look
    1.23
    ঠ
    1.23
     Faye
    1.19
     firmness
    1.19
     Advent
    1.16
    rocess
    1.14
     Vice
    1.13
    မြင့်
    1.13
    POSITIVE LOGITS
    ){}
    1.66
     فوتب
    1.53
     etcétera
    1.53
    нены
    1.51
    ){
    1.49
     genres
    1.45
     esempi
    1.44
    Nums
    1.44
     innumerable
    1.43
     incluyen
    1.43
    Activations Density 0.155%

    No Known Activations