© 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. 66917
    Prev
    Next
    INDEX
    Explanations

    phrases using specific prepositions

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

    data or code structure

    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
     الشيخ
    0.46
     Festival
    0.46
    тное
    0.45
    _;
    0.44
    eler
    0.44
     **
    0.41
     เช
    0.41
     Fats
    0.41
    plik
    0.41
     verdad
    0.40
    POSITIVE LOGITS
    砕
    0.45
    ğun
    0.45
     মুহুর্তে
    0.44
    Ĥ
    0.42
    랍니다
    0.41
    煩
    0.41
    烬
    0.40
    セキュリティ
    0.40
     blasted
    0.39
    وسیع
    0.39
    Activations Density 0.000%

    No Known Activations