© 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. 59588
    Prev
    Next
    INDEX
    Explanations

    Jerusalem, Sartre, Valentine

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

    skyrocketing growth

    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
    ו
    0.41
     पार्वती
    0.41
     lengkap
    0.41
     suka
    0.40
     sukar
    0.40
     citizen
    0.39
    saan
    0.39
     시민
    0.39
     estable
    0.38
     estabele
    0.38
    POSITIVE LOGITS
     moldings
    0.55
     pegged
    0.50
     canyons
    0.50
     Sartre
    0.47
     約
    0.47
     morphed
    0.47
     Earrings
    0.46
     achter
    0.46
     DPI
    0.45
     molds
    0.45
    Activations Density 0.000%

    No Known Activations