© 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. 18816
    Prev
    Next
    INDEX
    Explanations

    casino, our, 3, XC, World

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

    verb-noun pairs

    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
     SOLUTION
    0.50
     adimensional
    0.50
    PRES
    0.50
     चार्ज
    0.47
     न्यूज़
    0.47
     mathematical
    0.46
    㙂
    0.46
     следу
    0.46
     SCIENCE
    0.45
     све
    0.45
    POSITIVE LOGITS
    urados
    0.50
    其
    0.44
    ıyor
    0.44
    ؛
    0.43
    fois
    0.43
    né
    0.43
    nucle
    0.43
    ains
    0.42
    xtime
    0.42
    ⋙
    0.42
    Activations Density 0.000%

    No Known Activations