© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    intended audience or user type

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

    best for specific audiences

    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
     なさい
    0.37
     важней
    0.35
    ieken
    0.34
    死亡
    0.33
     सूत्रों
    0.33
     ইরা
    0.33
     exemplaire
    0.33
    ၆
    0.33
    proteins
    0.33
     আয়নের
    0.33
    POSITIVE LOGITS
     beginners
    0.74
     lovers
    0.71
    初心者
    0.66
     anyone
    0.63
    Anyone
    0.63
     enthusiasts
    0.63
     Anyone
    0.63
     beginner
    0.63
     amantes
    0.62
     discerning
    0.62
    Activations Density 0.484%

    No Known Activations