© 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. 706
    Prev
    Next
    INDEX
    Explanations

    crucial

    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
    t
    1.10
    ת
    0.89
    นี่
    0.87
    こと
    0.81
    თ
    0.80
    ը
    0.80
    ことがあります
    0.78
    了
    0.78
    d
    0.78
    tir
    0.78
    POSITIVE LOGITS
    uuuu
    1.53
    cci
    1.38
    arantee
    1.36
    ccess
    1.35
    pload
    1.31
    ğunu
    1.30
    uu
    1.26
    aranteed
    1.22
    hammad
    1.22
    rolog
    1.21
    Activations Density 0.401%

    No Known Activations