© 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. 247529
    Prev
    Next
    INDEX
    Explanations

    baby born

    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
    prac
    0.49
     Prac
    0.49
     које
    0.49
    𒉆
    0.48
     忄
    0.48
    пан
    0.47
     премии
    0.46
    颤
    0.46
     тихо
    0.46
     третье
    0.46
    POSITIVE LOGITS
    ِم
    0.46
    Warehouse
    0.42
    Karena
    0.41
    Mesh
    0.40
    TODO
    0.40
    FFA
    0.40
    Cell
    0.40
    ِل
    0.40
     manager
    0.39
    Machine
    0.39
    Activations Density 0.000%

    No Known Activations