© 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. 116687
    Prev
    Next
    INDEX
    Explanations

    even by / just make / capitalizing on

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

    quantifying relation, scale, or difference

    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
    does
    0.47
    sees
    0.45
    dW
    0.45
    ▛
    0.45
    uparavant
    0.45
    sling
    0.45
    lee
    0.44
    sit
    0.44
    stakes
    0.43
     t
    0.43
    POSITIVE LOGITS
     öğ
    0.46
     Organize
    0.46
     Genocide
    0.44
    ージャー
    0.44
     العلا
    0.44
    જન
    0.43
    ర్గ
    0.43
    гер
    0.43
    етесь
    0.43
    жный
    0.43
    Activations Density 0.000%

    No Known Activations