© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13439
    Prev
    Next
    INDEX
    Explanations

    `: ` followed by word, `=` followed by word, `.` followed by word

    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_13_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
    哂
    0.88
     Carlo
    0.85
    匚
    0.83
     contenidos
    0.83
     किन्तु
    0.82
    ຸນ
    0.82
     عنہ
    0.81
    <0x0C>
    0.80
     tattha
    0.80
    ども
    0.79
    POSITIVE LOGITS
    0.93
    个月
    0.91
    赤
    0.87
     Sol
    0.85
    是一
    0.85
    hw
    0.84
     a
    0.83
     ба
    0.83
     不
    0.82
     Elevation
    0.81
    Activations Density 0.060%

    No Known Activations