© 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. 26839
    Prev
    Next
    INDEX
    Explanations

    kinomes, wields, remove someone, high school, bootlegger

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

    English proficiency levels

    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
    或者是
    0.49
     或者
    0.42
    或者
    0.40
    或是
    0.39
    িয়া
    0.37
    𝑬
    0.35
    于是
    0.34
     "\
    0.33
    结点
    0.33
     কিংবা
    0.33
    POSITIVE LOGITS
     devenu
    0.45
     jamais
    0.43
     manusia
    0.42
     moderne
    0.42
     ikke
    0.41
     veramente
    0.41
     statesmen
    0.41
     wannan
    0.41
     použí
    0.40
     nostalg
    0.39
    Activations Density 0.001%

    No Known Activations