© 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. 18130
    Prev
    Next
    INDEX
    Explanations

    specific nouns and entities

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

    states or actions

    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
    ш
    0.44
     інших
    0.43
     downloading
    0.42
     використання
    0.42
     besser
    0.39
     изпол
    0.39
    日本では
    0.39
    ੪
    0.38
    下載
    0.38
    ⸩
    0.38
    POSITIVE LOGITS
     وكانت
    0.39
    很是
    0.39
     thankfully
    0.39
     مختصر
    0.38
     Thankfully
    0.38
    没有任何
    0.37
     그리고
    0.37
     incredibly
    0.37
     fürs
    0.37
    Thankfully
    0.36
    Activations Density 0.014%

    No Known Activations