© 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. 128735
    Prev
    Next
    INDEX
    Explanations

    places from, herbs, smell

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

    complex understanding

    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
    (
    0.47
     deteriorating
    0.47
     deterioration
    0.46
     مکمل
    0.43
     framework
    0.42
     ਹੈ
    0.42
     ち
    0.41
     somewhat
    0.41
     ਹੋ
    0.41
     epidemiology
    0.41
    POSITIVE LOGITS
     eléctricas
    0.58
     tỏa
    0.49
    })=\
    0.47
    тесь
    0.47
     électriques
    0.46
    ública
    0.46
    মুখে
    0.44
     municipales
    0.44
     escalas
    0.43
    胭
    0.43
    Activations Density 0.003%

    No Known Activations