© 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. 180893
    Prev
    Next
    INDEX
    Explanations

    US companies and you

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

    PlayStation 5 Console

    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
     Hurts
    0.50
    테
    0.49
    澧
    0.49
    ँच
    0.49
     renverse
    0.48
    媒介
    0.48
     элементы
    0.47
     органы
    0.46
    지역
    0.46
    ⚉
    0.46
    POSITIVE LOGITS
    rition
    0.50
    iness
    0.50
    rating
    0.49
    ravenous
    0.48
    lying
    0.48
    expect
    0.47
    dancing
    0.47
    known
    0.46
    udad
    0.46
     vista
    0.46
    Activations Density 0.000%

    No Known Activations