© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4809
    Prev
    Next
    INDEX
    Explanations

    command line prompt

    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
    ту
    0.72
    iten
    0.68
    assin
    0.66
    enk
    0.64
    }-{
    0.63
    inkler
    0.63
    cios
    0.62
    ลูกค้า
    0.60
    廪
    0.60
     அலுவலக
    0.60
    POSITIVE LOGITS
     misled
    0.69
     compete
    0.67
     World
    0.64
     competing
    0.64
     hear
    0.62
    Reality
    0.61
     answered
    0.61
     shook
    0.60
     answers
    0.60
     releg
    0.60
    Activations Density 0.130%

    No Known Activations