© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32909
    Prev
    Next
    INDEX
    Explanations

    purpose clauses

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

    purpose of systems

    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
     Praia
    0.40
     हुँ
    0.39
     Organiz
    0.38
    zló
    0.38
     Selangor
    0.38
    zył
    0.37
     sozinho
    0.37
     //}
    0.36
    وای
    0.36
     ४
    0.35
    POSITIVE LOGITS
     ताकि
    2.17
     تاکہ
    2.11
     zodat
    1.88
    เพื่อให้
    1.88
     ώστε
    1.79
     כדי
    1.76
     เพื่อ
    1.72
     чтобы
    1.70
    以便
    1.69
     যাতে
    1.66
    Activations Density 0.136%

    No Known Activations