© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2084
    Prev
    Next
    INDEX
    Explanations

    you might

    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
    鎸
    0.64
    TRUST
    0.63
    ことができる
    0.63
    ប់
    0.63
    ㄦ
    0.62
     Transforms
    0.61
     wyłącznie
    0.61
    लोग
    0.61
     exclusively
    0.60
    全て
    0.59
    POSITIVE LOGITS
    很有
    0.87
     most
    0.80
    風險
    0.80
     möglicherweise
    0.79
     muy
    0.78
     probably
    0.75
     risk
    0.74
     rất
    0.73
     nig
    0.73
    很
    0.73
    Activations Density 0.311%

    No Known Activations