© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3389
    Prev
    Next
    INDEX
    Explanations

    atoms and molecules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ра
    1.01
    כ
    0.94
    ما
    0.91
    ма
    0.90
    دی
    0.90
    ↵↵
    0.89
    دي
    0.87
    点で
    0.83
    ۷
    0.83
    ۸
    0.82
    POSITIVE LOGITS
     Molecule
    1.23
     molecules
    1.07
     Molecular
    1.07
     Molecules
    1.06
    g
    1.05
     molecular
    1.04
     molecule
    1.02
     molécule
    0.95
     that
    0.95
    ero
    0.90
    Activations Density 0.010%

    No Known Activations