© 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. 9924
    Prev
    Next
    INDEX
    Explanations

    crucial for robustness

    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
     (+
    1.80
     (&
    1.78
     (~
    1.78
     (/
    1.71
     ('
    1.69
     (-
    1.68
     (‘
    1.60
    !(
    1.55
     (
    1.53
    /(
    1.52
    POSITIVE LOGITS
    っていう
    2.03
     kind
    2.01
     basically
    1.90
    basically
    1.74
     sort
    1.74
     kinda
    1.64
    Yeah
    1.62
     Yeah
    1.59
     actually
    1.59
     really
    1.58
    Activations Density 0.206%

    No Known Activations