© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14932
    Prev
    Next
    INDEX
    Explanations

    common phrases after nouns

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

    deeper into relaxation

    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
     ھ
    0.45
     Inhibition
    0.41
     Oiseau
    0.41
     Aquare
    0.39
     lymphocyte
    0.38
     Metropolis
    0.38
     amma
    0.38
     perempuan
    0.38
     Num
    0.38
     Leibniz
    0.38
    POSITIVE LOGITS
    argu
    0.45
    при
    0.43
    по
    0.42
    реа
    0.41
    <unused2024>
    0.41
     структур
    0.40
    ੌਰ
    0.40
    큼
    0.40
    PLEASE
    0.39
    о
    0.39
    Activations Density 0.604%

    No Known Activations