© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73990
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "he"

    np_acts-logits-general · gemini-2.5-flash-lite

    i wonder can examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Ц
    0.61
    Jetzt
    0.59
    צ
    0.57
    Nicht
    0.55
     Möglichkeit
    0.55
    Yep
    0.55
    Unser
    0.55
    д
    0.54
    Spiel
    0.53
    Фі
    0.52
    POSITIVE LOGITS
     whereof
    0.62
     hereby
    0.59
     geometrical
    0.58
     هولندا
    0.56
     Dutch
    0.56
     hereof
    0.55
     colourful
    0.54
     colours
    0.53
     Furthermore
    0.53
     thereof
    0.52
    Activations Density 0.122%

    No Known Activations