© 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. 216630
    Prev
    Next
    INDEX
    Explanations

    events, postponed, trying

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

    refrigerator, fridge, screen, switches, diet

    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
    rektor
    0.55
     聞い
    0.53
    resultlist
    0.49
    ılarak
    0.48
    ‌లో
    0.47
    centro
    0.47
     AML
    0.45
    ˒
    0.45
    autore
    0.45
    Centro
    0.45
    POSITIVE LOGITS
     placés
    0.42
    飕
    0.41
    يذ
    0.41
     outbreaks
    0.40
    神的
    0.40
     frü
    0.40
    щей
    0.39
     entstehen
    0.39
     §
    0.39
     soil
    0.39
    Activations Density 0.000%

    No Known Activations