© 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. 87562
    Prev
    Next
    INDEX
    Explanations

    reasons why

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

    hydrogen and helium

    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
    yak
    0.55
    on
    0.54
    a
    0.54
    u
    0.54
    uk
    0.53
    yu
    0.53
    il
    0.53
    at
    0.52
    ı
    0.52
    Introduction
    0.51
    POSITIVE LOGITS
     gazebo
    0.50
     βοη
    0.50
     γλώ
    0.49
     bắc
    0.48
     sneeze
    0.48
     নৌ
    0.48
     Mord
    0.48
     actividad
    0.47
     hangar
    0.47
     মিনি
    0.47
    Activations Density 0.003%

    No Known Activations