© 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. 3145
    Prev
    Next
    INDEX
    Explanations

    qualifiers and negative descriptors

    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
     Trouble
    0.82
     Dangerous
    0.79
    Dangerous
    0.78
     trouble
    0.76
    坏
    0.76
    壞
    0.75
     dangerous
    0.74
     dangerously
    0.74
     disgraceful
    0.74
    不好
    0.73
    POSITIVE LOGITS
     jeweiligen
    0.72
     gleichen
    0.67
     school
    0.66
     overwhelming
    0.66
     बूथ
    0.66
    ảng
    0.65
    蔻
    0.65
     zunächst
    0.65
     dated
    0.64
     welchem
    0.64
    Activations Density 0.330%

    No Known Activations