© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4228
    Prev
    Next
    INDEX
    Explanations

    web addresses with periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    de
    0.85
     تازه
    0.80
     از
    0.79
    夺
    0.79
    ätt
    0.78
    奔驰
    0.77
    arım
    0.77
    ację
    0.74
    ująca
    0.74
    ække
    0.73
    POSITIVE LOGITS
    .
    0.76
    .=
    0.69
    ./
    0.69
    .”[
    0.67
    .?
    0.65
    .,
    0.64
    .$.
    0.64
    
    0.63
     disciplined
    0.63
     manipulated
    0.63
    Activations Density 0.060%

    No Known Activations