© 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. 2657
    Prev
    Next
    INDEX
    Explanations

    budget estimation

    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
    へと
    0.80
     appreciably
    0.75
    berat
    0.74
    நீ
    0.73
    юро
    0.71
    Approximately
    0.71
    約
    0.71
     noticeably
    0.69
    憫
    0.68
     roughly
    0.68
    POSITIVE LOGITS
     speaking
    0.76
     sia
    0.69
     falar
    0.67
     palavra
    0.67
     Range
    0.65
     Speaking
    0.65
     speak
    0.65
     parola
    0.64
     inser
    0.64
     fala
    0.63
    Activations Density 0.075%

    No Known Activations