© 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. 17-GEMMASCOPE-2-RES-16K
    7. 639
    Prev
    Next
    INDEX
    Explanations

    * symbol formatting

    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_17_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
     perceptions
    1.00
     iterative
    0.99
    <unused357>
    0.98
    <unused411>
    0.97
     thoughtful
    0.97
     plausible
    0.97
    <unused1071>
    0.95
    <unused744>
    0.94
     considerations
    0.93
    <unused1903>
    0.93
    POSITIVE LOGITS
     ook
    0.81
     فلا
    0.69
     was
    0.69
    创立
    0.67
     byli
    0.66
     blev
    0.65
     comprado
    0.65
     werd
    0.64
    是由
    0.64
    Ch
    0.64
    Activations Density 0.791%

    No Known Activations