© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1376
    Prev
    Next
    INDEX
    Explanations

    AddTrack function call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    1.15
    <i>
    1.14
    <b>
    1.05
    <sup>
    1.05
    <u>
    1.05
    atsi
    1.05
    </i>
    1.03
    <sub>
    1.03
    ↵
    0.98
      
    0.97
    POSITIVE LOGITS
     These
    2.95
     This
    2.94
     There
    2.87
     Although
    2.78
     However
    2.71
     If
    2.67
     The
    2.65
     While
    2.64
     Как
    2.61
     When
    2.55
    Activations Density 4.814%

    No Known Activations