© 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. 1240
    Prev
    Next
    INDEX
    Explanations

    do you want

    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
     اقبال
    0.71
    ామ
    0.71
    Cxt
    0.70
    ֖
    0.69
    मिक
    0.69
     அதிகமாக
    0.66
    に入れる
    0.66
    梸
    0.66
     CONSIDER
    0.66
    ֛
    0.64
    POSITIVE LOGITS
     would
    1.33
    would
    1.24
     Would
    1.21
     want
    1.18
    Would
    1.18
     Want
    1.10
    Want
    1.08
     wants
    1.01
     ingin
    1.01
    want
    1.00
    Activations Density 0.459%

    No Known Activations