© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6379
    Prev
    Next
    INDEX
    Explanations

    code blocks ending punctuation

    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
    levance
    0.61
    ảnh
    0.58
     చెందిన
    0.57
    cular
    0.56
    <eos>
    0.50
     alt
    0.50
    خرى
    0.50
     possibilit
    0.50
     nargs
    0.49
    哚
    0.48
    POSITIVE LOGITS
     jewel
    0.88
     owed
    0.87
    沨
    0.84
     Jewel
    0.82
    งาม
    0.81
     wound
    0.81
     Raw
    0.80
    红色
    0.80
    ↵
    0.79
     Walls
    0.79
    Activations Density 0.036%

    No Known Activations