© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167854
    Prev
    Next
    INDEX
    Explanations

    saving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    юм
    0.40
     immediately
    0.40
    τως
    0.37
    粈
    0.37
    唖
    0.37
     после
    0.37
     worrisome
    0.37
     զ
    0.36
    อย่าง
    0.36
     після
    0.36
    POSITIVE LOGITS
     Saves
    0.54
     Save
    0.53
    Save
    0.51
    保存
    0.51
    save
    0.49
     保存
    0.48
     SAVE
    0.47
    generators
    0.45
     save
    0.45
    saves
    0.43
    Activations Density 0.001%

    No Known Activations