© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11433
    Prev
    Next
    INDEX
    Explanations

    pneumothorax

    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_7_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
     ‘
    2.28
     “
    2.25
     The
    2.05
     ’
    2.01
      
    2.01
     ”
    1.83
    The
    1.67
     built
    1.66
     어
    1.65
    <eos>
    1.59
    POSITIVE LOGITS
     moguć
    3.14
    ו
    3.01
    <unused821>
    2.97
    btree
    2.91
    lamualaikum
    2.86
    <unused392>
    2.85
    र्दू
    2.84
    𒄑
    2.84
     impresora
    2.82
    ल
    2.81
    Activations Density 0.040%

    No Known Activations