© 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. 228866
    Prev
    Next
    INDEX
    Explanations

    God, good, supportive, loan, protein

    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
     Sturgeon
    0.51
    λη
    0.49
    ων
    0.44
    Palmer
    0.44
     tor
    0.43
     Palmer
    0.43
    ,
    0.42
     towing
    0.41
    能
    0.41
     STL
    0.41
    POSITIVE LOGITS
     उसमे
    0.49
    itemap
    0.46
     странах
    0.46
     विशेषताएं
    0.45
     கட்டமை
    0.45
    地说
    0.45
     اقسام
    0.45
    大战
    0.45
     страницы
    0.44
     destac
    0.44
    Activations Density 0.001%

    No Known Activations