© 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. 4301
    Prev
    Next
    INDEX
    Explanations

    number 3 or three followed by colon

    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
     inay
    0.68
     Архивная
    0.68
    iende
    0.67
    侧
    0.67
     नीड
    0.66
    Comté
    0.66
     Matter
    0.65
    :$
    0.65
     doubleheader
    0.65
     والس
    0.64
    POSITIVE LOGITS
     three
    1.22
    three
    1.16
    3
    1.04
    三种
    1.04
    ３
    1.02
    三个
    1.01
     tiga
    1.00
    Three
    1.00
    
    0.99
     third
    0.99
    Activations Density 0.104%

    No Known Activations